© 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. 13660
    Prev
    Next
    INDEX
    Explanations

    terms related to different ancient cultures and astrology, particularly focusing on Greek, Indian, Hebrew, and Persian origins

    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
    +0.14
    0.6%
    288
    +0.13
    0.6%
    267
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.14
    0.08
    656
    +0.13
    0.08
    640
    +0.10
    0.19
    Negative Logits
    alties
    -0.96
    ufact
    -0.90
    lease
    -0.90
    inson
    -0.88
    illance
    -0.88
    ertodd
    -0.86
    vable
    -0.85
    redo
    -0.83
    inez
    -0.81
    rences
    -0.81
    POSITIVE LOGITS
     proverb
    0.95
     Nadu
    0.94
     language
    0.92
     ancestry
    0.91
     Language
    0.88
     languages
    0.87
    istani
    0.87
     accents
    0.87
     dialect
    0.85
     Orthodox
    0.85
    Activations Density 9.095%

    No Known Activations