© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 33756
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    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
    184
    +0.12
    0.5%
    397
    +0.10
    0.5%
    482
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.12
    0.26
    107
    +0.10
    0.06
    6
    +0.10
    0.15
    Negative Logits
    ãĤ¤ãĥĪ
    -0.72
    aroo
    -0.69
    vertisement
    -0.69
    é¾
    -0.68
    »Ĵ
    -0.68
    HAHAHAHA
    -0.65
     Palest
    -0.65
     clicked
    -0.62
     Pigs
    -0.61
    ij士
    -0.61
    POSITIVE LOGITS
    eper
    0.74
    arth
    0.74
    igham
    0.74
    aults
    0.74
     Finn
    0.72
    Marie
    0.71
    ĸļ
    0.70
    ucker
    0.69
    abo
    0.68
    ecast
    0.67
    Activations Density 12.940%

    No Known Activations