© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 13156
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly those involved in sports or legal cases

    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
    447
    +0.18
    0.8%
    326
    +0.17
    0.7%
    526
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.18
    0.21
    288
    +0.17
    0.20
    659
    +0.14
    0.10
    Negative Logits
    ãĥīãĥ©
    -0.88
    fm
    -0.86
    circ
    -0.82
    ãĤ¦ãĤ¹
    -0.82
    pection
    -0.80
    schild
    -0.79
    inators
    -0.77
    ãĥ«
    -0.75
    ãĥĪ
    -0.74
    edition
    -0.74
    POSITIVE LOGITS
     Wink
    1.02
     Tyler
    0.87
     Shields
    0.84
    burgh
    0.80
    warm
    0.79
     Cow
    0.77
     Strait
    0.76
     Skywalker
    0.75
     Bridges
    0.75
    stown
    0.74
    Activations Density 6.147%

    No Known Activations