© 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
    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. 39874
    Prev
    Next
    INDEX
    Explanations

    names related to a specific character

    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
    +0.13
    0.7%
    35
    +0.12
    0.6%
    554
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.17
    282
    +0.12
    0.09
    326
    +0.11
    0.16
    Negative Logits
    mble
    -0.75
    ulhu
    -0.69
    habi
    -0.68
    llor
    -0.68
    arching
    -0.66
    essor
    -0.62
    BOOK
    -0.62
    yip
    -0.62
    eanor
    -0.62
    engers
    -0.62
    POSITIVE LOGITS
     Twist
    0.85
    sson
    0.75
     Oliver
    0.75
     Wend
    0.71
     Crom
    0.67
    tein
    0.66
     Klein
    0.65
    alia
    0.64
    Wheel
    0.63
    nel
    0.62
    Activations Density 4.965%

    No Known Activations