© 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. 33558
    Prev
    Next
    INDEX
    Explanations

    phrases related to cities 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
    99
    +0.14
    0.7%
    421
    +0.13
    0.6%
    16
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.14
    0.10
    288
    +0.13
    0.16
    721
    +0.11
    0.06
    Negative Logits
    ãĥ¼ãĥ³
    -0.74
     Skywalker
    -0.66
    Raid
    -0.66
    Wan
    -0.66
    VIDEO
    -0.66
     STOR
    -0.64
    PRESS
    -0.64
    xon
    -0.63
    enegger
    -0.63
    edu
    -0.62
    POSITIVE LOGITS
    teenth
    1.04
    ouse
    0.99
    igans
    0.95
    otaur
    0.94
    oir
    0.94
    inic
    0.94
    otine
    0.87
    istic
    0.87
    mosp
    0.87
    sen
    0.85
    Activations Density 5.117%

    No Known Activations