© 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. 34971
    Prev
    Next
    INDEX
    Explanations

    references to physical attributes or states

    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
    649
    +0.18
    0.7%
    447
    +0.18
    0.7%
    288
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    569
    +0.18
    0.08
    669
    +0.18
    0.07
    289
    +0.13
    0.00
    Negative Logits
    adish
    -0.90
    ungle
    -0.89
    shire
    -0.88
    stellar
    -0.87
    quist
    -0.86
    ered
    -0.85
    emi
    -0.81
    bare
    -0.81
    later
    -0.79
    CHAT
    -0.79
    POSITIVE LOGITS
     manifestation
    1.12
    ity
    1.11
     impossibility
    1.06
     sciences
    0.98
    ized
    0.98
     manifestations
    0.97
     altercation
    0.97
    anguage
    0.95
     objects
    0.93
     deform
    0.93
    Activations Density 5.682%

    No Known Activations