© 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. 33817
    Prev
    Next
    INDEX
    Explanations

    specific named entities or organizations related to various contexts, such as individuals, institutions, or locations

    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
    59
    +0.12
    0.6%
    326
    +0.09
    0.4%
    240
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.25
    288
    +0.09
    0.27
    401
    +0.09
    0.15
    Negative Logits
    ivities
    -0.79
    ERAL
    -0.78
    ãĤ¼ãĤ¦ãĤ¹
    -0.73
    utterstock
    -0.72
    ancial
    -0.72
    ingers
    -0.71
    aign
    -0.70
    itol
    -0.69
    acters
    -0.69
    idential
    -0.68
    POSITIVE LOGITS
    yssey
    0.92
    scill
    0.79
    cean
    0.73
     XIII
    0.73
    sett
    0.73
    live
    0.71
    tto
    0.71
    zzi
    0.69
    toc
    0.68
    boro
    0.68
    Activations Density 9.243%

    No Known Activations