© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12627
    Prev
    Next
    INDEX
    Explanations

    references to age, specifically highlighting the concept of being the oldest or youngest in various contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.13
    0.6%
    72
    +0.11
    0.5%
    262
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    122
    +0.13
    0.06
    162
    +0.11
    0.05
    339
    +0.10
    0.05
    Negative Logits
    bara
    -0.89
    ontent
    -0.79
    rompt
    -0.78
    par
    -0.78
    redo
    -0.77
    odium
    -0.77
    lim
    -0.76
    roth
    -0.75
    stri
    -0.75
    ending
    -0.75
    POSITIVE LOGITS
     conceivable
    1.01
     possible
    0.92
     extant
    0.91
     ever
    0.85
     imaginable
    0.83
     practicable
    0.82
     arri
    0.81
     surviving
    0.77
     incarnation
    0.76
     achievable
    0.75
    Activations Density 0.733%

    No Known Activations