© 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
    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. 40497
    Prev
    Next
    INDEX
    Explanations

    discussions on political ideologies, specifically related to anarchist and socialist concepts

    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
    756
    +0.13
    0.7%
    9
    +0.11
    0.6%
    113
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.25
    18
    +0.11
    0.11
    756
    +0.11
    -0.15
    Negative Logits
    Alert
    -0.80
    CLOSE
    -0.70
    CLAIM
    -0.68
    Pokemon
    -0.68
    Buzz
    -0.66
    Stretch
    -0.63
    Larry
    -0.62
    Wow
    -0.62
    Todd
    -0.62
    ï¸ı
    -0.61
    POSITIVE LOGITS
     proletariat
    0.83
     Luxem
    0.83
     revolt
    0.78
    arist
    0.77
     Bolshe
    0.77
     prolet
    0.76
     Engels
    0.75
     anarchism
    0.75
     bourgeoisie
    0.75
     Anarch
    0.74
    Activations Density 11.241%

    No Known Activations