© 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. 33779
    Prev
    Next
    INDEX
    Explanations

    information related to urban development and community planning, possibly focusing on sports facilities

    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
    1
    +0.13
    0.6%
    447
    +0.12
    0.5%
    172
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.13
    0.30
    255
    +0.12
    0.13
    573
    +0.11
    0.05
    Negative Logits
    ģĸ
    -0.87
    士
    -0.73
    å°Ĩ
    -0.72
    ij士
    -0.71
    ĸļ
    -0.70
    FUL
    -0.66
    etus
    -0.65
     acknow
    -0.65
    kefeller
    -0.64
    ©¶æ¥µ
    -0.64
    POSITIVE LOGITS
    styles
    0.78
    atin
    0.75
    rouse
    0.71
    atto
    0.69
    uben
    0.68
    achus
    0.67
    ickets
    0.66
    aneously
    0.65
    jug
    0.65
    pell
    0.64
    Activations Density 18.434%

    No Known Activations