© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1213
    Prev
    Next
    INDEX
    Explanations

    information related to sports games, players, practices, and interactions between coaches and players

    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
    640
    +0.48
    1.6%
    649
    +0.20
    0.7%
    5
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.48
    0.20
    64
    +0.20
    -0.06
    94
    +0.15
    0.12
    Negative Logits
     incarn
    -1.11
    ijing
    -1.07
     Reincarnated
    -1.05
    ardless
    -1.04
     wiser
    -1.04
    otine
    -1.03
    boro
    -1.02
    heit
    -1.01
    gebra
    -1.01
    sterdam
    -1.00
    POSITIVE LOGITS
    ONSORED
    1.48
    Refer
    1.41
    Indeed
    1.39
    Testing
    1.37
    Newsletter
    1.34
    Asked
    1.26
    However
    1.26
    SPONSORED
    1.25
    Instead
    1.22
    Nonetheless
    1.22
    Activations Density 1.571%

    No Known Activations