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

    Neuronpedia

    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. 13334
    Prev
    Next
    INDEX
    Explanations

    phrases related to political debates

    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
    +0.16
    0.6%
    268
    +0.13
    0.5%
    538
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.12
    519
    +0.13
    0.06
    651
    +0.12
    0.07
    Negative Logits
    aples
    -0.92
    reads
    -0.92
    phia
    -0.89
    ient
    -0.86
    uria
    -0.85
    ikes
    -0.85
    esthetic
    -0.84
    ience
    -0.83
    relative
    -0.83
    istic
    -0.83
    POSITIVE LOGITS
     schedule
    0.92
     season
    0.91
     schedules
    0.83
     jugg
    0.80
    querque
    0.79
     contestant
    0.79
     endorsements
    0.76
     kickoff
    0.75
     commencement
    0.74
     contestants
    0.74
    Activations Density 1.204%

    No Known Activations