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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 32766
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and terms related to political actions and contexts

    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
    +0.22
    1.4%
    481
    +0.07
    0.5%
    430
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    521
    +0.22
    0.03
    430
    +0.07
    0.19
    294
    +0.07
    0.04
    Negative Logits
     Hawai
    -0.61
    Seattle
    -0.56
    Ô
    -0.55
     Gree
    -0.55
     Honolulu
    -0.55
    uebl
    -0.51
    ¥µ
    -0.50
     Chero
    -0.50
     Iro
    -0.50
     Judah
    -0.50
    POSITIVE LOGITS
     appoint
    0.60
     urgently
    0.58
     ministers
    0.58
     reassured
    0.56
     congratulated
    0.54
     ministerial
    0.53
     reassure
    0.53
     cabinet
    0.53
     MEP
    0.52
     pledged
    0.51
    Activations Density 11.488%

    No Known Activations