© 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. 32878
    Prev
    Next
    INDEX
    Explanations

    the concept of actions or events happening to multiple individuals

    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
    566
    +0.09
    0.5%
    113
    +0.08
    0.5%
    84
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.09
    0.15
    107
    +0.08
    0.10
    326
    +0.07
    0.20
    Negative Logits
    mun
    -0.70
    ayer
    -0.70
    VERTISEMENT
    -0.66
    bour
    -0.65
    pher
    -0.65
    Assembly
    -0.64
    hare
    -0.64
    met
    -0.63
    ware
    -0.62
    meter
    -0.60
    POSITIVE LOGITS
    Ń·
    0.74
    Û
    0.71
    ©
    0.70
    ¡
    0.69
    Í
    0.66
    ĩ
    0.63
    Į
    0.63
    veyard
    0.62
    ľ
    0.59
    alore
    0.58
    Activations Density 5.402%

    No Known Activations