© 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 EvalsExportsinterp-engineNEWAPI 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. 32180
    Prev
    Next
    INDEX
    Explanations

    word pairs or phrases related to various forms of creative work like music, movies, and shows

    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
    640
    +0.14
    1.2%
    447
    +0.10
    0.9%
    414
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.14
    0.45
    6
    +0.10
    0.26
    64
    +0.06
    -0.25
    Negative Logits
    ername
    -0.39
     milit
    -0.39
     pensions
    -0.38
    pace
    -0.36
    paces
    -0.36
     Medicare
    -0.36
    76561
    -0.36
    ocrin
    -0.35
    urance
    -0.35
    abwe
    -0.34
    POSITIVE LOGITS
    Winner
    0.49
     Featuring
    0.46
    Released
    0.46
    Adapt
    0.44
     Drawn
    0.43
    Music
    0.43
     Drama
    0.42
    Includes
    0.40
     Album
    0.40
     soundtrack
    0.40
    Activations Density 13.509%

    No Known Activations