© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 6272
    Prev
    Next
    INDEX
    Explanations

    phrases related to entities and specific names, likely focusing on some form of identification or categorization

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    16
    +0.10
    0.7%
    554
    +0.07
    0.5%
    725
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.10
    -0.00
    406
    +0.07
    0.01
    659
    +0.07
    0.01
    Negative Logits
    abilities
    -0.53
    olicy
    -0.49
    attacks
    -0.47
    alyses
    -0.46
    etics
    -0.46
    sb
    -0.45
    ograms
    -0.45
    lua
    -0.45
    rogram
    -0.45
    ©¶æ
    -0.44
    POSITIVE LOGITS
    ORN
    0.64
    ULE
    0.53
    OCK
    0.49
    TON
    0.49
    EGIN
    0.47
    ATOR
    0.44
    Ò
    0.44
    FORE
    0.44
     hon
    0.44
    CLASSIFIED
    0.43
    Activations Density 0.006%

    No Known Activations