© 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. 14033
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and related programming terminologies

    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
    2
    +0.06
    0.4%
    102
    +0.06
    0.4%
    366
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.06
    0.21
    373
    +0.06
    -0.16
    217
    +0.06
    0.06
    Negative Logits
    estones
    -0.56
    gaard
    -0.52
     arsen
    -0.48
    thur
    -0.46
    alities
    -0.44
    erves
    -0.42
    cture
    -0.42
    uckland
    -0.42
    asio
    -0.42
    ality
    -0.41
    POSITIVE LOGITS
    string
    0.48
    Block
    0.45
    Document
    0.44
    Container
    0.44
    Usage
    0.44
    Shell
    0.44
    Che
    0.43
    ual
    0.43
     Fields
    0.43
    Field
    0.43
    Activations Density 7.189%

    No Known Activations