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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 34493
    Prev
    Next
    INDEX
    Explanations

    phrases related to leadership qualities or descriptions in a sports-related context

    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
    447
    +0.11
    1.2%
    454
    +0.05
    0.5%
    307
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.11
    0.27
    620
    +0.05
    0.03
    283
    +0.04
    0.01
    Negative Logits
    veh
    -0.29
    irming
    -0.28
     SQ
    -0.27
    zar
    -0.26
    asonic
    -0.26
    inion
    -0.25
    usions
    -0.24
    issions
    -0.24
     Kah
    -0.24
    tein
    -0.23
    POSITIVE LOGITS
    yip
    0.37
     nightmares
    0.33
     envy
    0.31
     attracts
    0.30
    veyard
    0.29
     caricature
    0.27
     envis
    0.26
     entails
    0.26
    uman
    0.25
     nightmare
    0.25
    Activations Density 11.578%

    No Known Activations