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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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 Local
    9. 6-RES_SCL-AJT
    11. 33102
    Prev
    Next
    INDEX
    Explanations

    phrases related to urban development and community well-being

    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
    +0.23
    1.4%
    481
    +0.17
    1.0%
    341
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.23
    0.30
    119
    +0.17
    0.14
    481
    +0.09
    0.28
    Negative Logits
    ãĤ´ãĥ³
    -0.53
    uyomi
    -0.52
    ocracy
    -0.50
    democracy
    -0.48
     financing
    -0.48
    atlantic
    -0.46
    burning
    -0.46
    jury
    -0.46
    zai
    -0.45
    politics
    -0.43
    POSITIVE LOGITS
     ones
    0.62
     succumb
    0.49
     are
    0.48
    went
    0.47
     succumbed
    0.47
     Ones
    0.47
     complain
    0.46
     resorted
    0.46
     reproduce
    0.46
    ilers
    0.46
    Activations Density 14.755%

    No Known Activations