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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13708
    Prev
    Next
    INDEX
    Explanations

    information related to sports drafts

    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
    438
    +0.12
    0.6%
    600
    +0.10
    0.5%
    386
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.12
    0.24
    640
    +0.10
    0.21
    571
    +0.08
    0.09
    Negative Logits
     outage
    -0.74
     fires
    -0.73
     vigil
    -0.71
     vibrations
    -0.70
     cafes
    -0.66
     erupt
    -0.66
     pests
    -0.65
     deterior
    -0.64
    pace
    -0.64
    xual
    -0.62
    POSITIVE LOGITS
     waivers
    0.96
    Draft
    0.87
     Rookie
    0.82
     lottery
    0.82
     prestigious
    0.77
    eligible
    0.76
     Draft
    0.76
     Heisman
    0.76
     draft
    0.74
     undrafted
    0.72
    Activations Density 10.105%

    No Known Activations