Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13914
    Prev
    Next
    INDEX
    Explanations

    mentions of physical changes and experiences related to transitioning and gender identity

    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
    82
    +0.13
    0.5%
    267
    +0.12
    0.5%
    129
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.13
    0.07
    59
    +0.12
    0.06
    618
    +0.12
    0.09
    Negative Logits
    allery
    -0.88
    redo
    -0.86
    atures
    -0.85
    auder
    -0.82
    yet
    -0.79
    auntlet
    -0.78
    utterstock
    -0.78
    abil
    -0.78
    pires
    -0.77
    claimer
    -0.76
    POSITIVE LOGITS
     brainstorm
    0.86
     Psychiat
    0.81
     my
    0.77
    okingly
    0.77
     Nights
    0.77
     Mahjong
    0.74
     Nin
    0.74
     visiting
    0.74
     Called
    0.74
     slang
    0.74
    Activations Density 3.978%

    No Known Activations