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 Local
    5. 6-RES_SCL-AJT
    6. 4275
    Prev
    Next
    INDEX
    Explanations

    words related to physical hygiene and cleanliness

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    195
    +0.06
    0.6%
    643
    +0.05
    0.5%
    205
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    28
    +0.06
    0.11
    326
    +0.05
    0.25
    643
    +0.05
    0.06
    Negative Logits
    ramer
    -0.38
    ertain
    -0.37
    rals
    -0.36
    yers
    -0.35
     livest
    -0.34
    raine
    -0.32
    lov
    -0.32
    elsen
    -0.32
    rn
    -0.31
    binding
    -0.31
    POSITIVE LOGITS
     flush
    0.54
     flushed
    0.51
     toilets
    0.43
     Meadows
    0.38
     cheeks
    0.37
     blush
    0.35
    nery
    0.33
    itant
    0.33
    ting
    0.32
    ishable
    0.32
    Activations Density 9.868%

    No Known Activations