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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45168
    Prev
    Next
    INDEX
    Explanations

    references to organizations and initiatives related to the LGBTQ+ community

    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
    393
    +0.07
    0.6%
    447
    +0.07
    0.6%
    46
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.07
    0.43
    640
    +0.07
    0.36
    375
    +0.05
    0.10
    Negative Logits
    orrow
    -0.39
    lier
    -0.39
    lain
    -0.38
    lamm
    -0.37
    ugi
    -0.34
    overe
    -0.34
    lay
    -0.34
    own
    -0.34
    hov
    -0.33
    ngth
    -0.33
    POSITIVE LOGITS
    romeda
    0.35
     vice
    0.33
     then
    0.32
     nephew
    0.32
     other
    0.31
     progressive
    0.30
     Torres
    0.29
     related
    0.29
     blues
    0.29
     maths
    0.28
    Activations Density 21.349%

    No Known Activations