© 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. 329
    Prev
    Next
    INDEX
    Explanations

    commentary text typically found in online forums

    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
    311
    +0.12
    0.6%
    514
    +0.11
    0.5%
    683
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.12
    0.02
    514
    +0.11
    0.01
    76
    +0.09
    0.02
    Negative Logits
     liquids
    -0.76
     Palest
    -0.71
     sights
    -0.67
    iott
    -0.66
     pel
    -0.66
    negie
    -0.66
     impacted
    -0.66
    weights
    -0.66
    atform
    -0.63
     hurd
    -0.63
    POSITIVE LOGITS
    malink
    0.76
    :]
    0.75
    idy
    0.73
    naire
    0.72
    lishing
    0.71
    gment
    0.70
    éĸ
    0.67
    emn
    0.67
    Grey
    0.66
    Legendary
    0.66
    Activations Density 0.158%

    No Known Activations