© 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. 33479
    Prev
    Next
    INDEX
    Explanations

    specific geometric shapes

    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
    213
    +0.11
    0.6%
    288
    +0.11
    0.5%
    503
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.11
    -0.01
    111
    +0.11
    0.06
    288
    +0.10
    0.16
    Negative Logits
    ARK
    -0.71
    UGH
    -0.63
    âĸ¬âĸ¬
    -0.60
    PLIED
    -0.59
     waivers
    -0.59
     Resistance
    -0.58
    اÙĦ
    -0.56
    ÙIJ
    -0.56
     bees
    -0.56
     Sons
    -0.55
    POSITIVE LOGITS
    angles
    1.09
    angular
    1.04
    rect
    0.97
     rect
    0.96
    uitous
    0.96
    rices
    0.93
    angle
    0.90
    ified
    0.86
    angelo
    0.83
    izon
    0.83
    Activations Density 6.178%

    No Known Activations