© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 13387
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and names

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    566
    +0.15
    0.5%
    216
    +0.14
    0.5%
    288
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.10
    326
    +0.14
    0.08
    659
    +0.13
    0.05
    Negative Logits
    à¼
    -0.93
    matter
    -0.91
    istant
    -0.87
    alam
    -0.84
     Emerald
    -0.84
    ividual
    -0.82
    UAL
    -0.81
    ually
    -0.81
     IST
    -0.79
    ilated
    -0.79
    POSITIVE LOGITS
    dden
    1.56
    kefeller
    1.30
    ppo
    1.29
    opa
    1.20
    sters
    1.19
    phies
    1.19
    opers
    1.19
    culosis
    1.18
    tro
    1.13
     Tro
    1.12
    Activations Density 1.273%

    No Known Activations