© 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. 45810
    Prev
    Next
    INDEX
    Explanations

    political terms and mentions of political parties

    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
    7
    +0.09
    0.5%
    752
    +0.09
    0.5%
    330
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    24
    +0.09
    0.09
    247
    +0.09
    0.09
    662
    +0.08
    0.10
    Negative Logits
     Asgard
    -0.61
     âĸĪ
    -0.57
     Sina
    -0.56
    bourne
    -0.56
     fools
    -0.56
     Britann
    -0.54
     Everett
    -0.54
     Reloaded
    -0.54
     Gutenberg
    -0.53
     Runes
    -0.53
    POSITIVE LOGITS
    abulary
    0.68
    cill
    0.62
    papers
    0.58
    ourke
    0.58
    istrates
    0.57
    udeb
    0.56
    agent
    0.56
    onnaissance
    0.56
     chair
    0.56
    ournals
    0.55
    Activations Density 10.761%

    No Known Activations