© 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. 31538
    Prev
    Next
    INDEX
    Explanations

    words related to physical movement or actions involving dropping or falling

    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
    569
    +0.11
    0.6%
    659
    +0.10
    0.5%
    316
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.11
    0.04
    416
    +0.10
    0.06
    569
    +0.09
    0.06
    Negative Logits
     Trident
    -0.68
    ãĥ¼ãĥĨ
    -0.66
     Canary
    -0.64
    ãĥ¯ãĥ³
    -0.63
    ãĥĨãĤ£
    -0.63
    é¾įå¥ij士
    -0.61
     Clause
    -0.61
    ãĤ¢ãĥ«
    -0.59
     à¨
    -0.59
     Ou
    -0.59
    POSITIVE LOGITS
    plets
    1.13
    plet
    1.12
    ppers
    1.01
    pper
    0.92
    ves
    0.88
    ppings
    0.83
    cks
    0.80
    opa
    0.77
    opy
    0.76
    vable
    0.76
    Activations Density 9.381%

    No Known Activations