© 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. 14155
    Prev
    Next
    INDEX
    Explanations

    information about places and events

    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
    393
    +0.34
    1.2%
    362
    +0.19
    0.6%
    385
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.34
    0.14
    92
    +0.19
    0.10
    562
    +0.18
    0.09
    Negative Logits
     Ukrain
    -0.93
     Worse
    -0.92
     Recomm
    -0.90
     Frazier
    -0.90
    ju
    -0.90
    erc
    -0.89
    endif
    -0.89
    Bear
    -0.88
    Loading
    -0.88
    opers
    -0.86
    POSITIVE LOGITS
     own
    2.27
     newfound
    1.42
     respective
    1.37
     predecessors
    1.30
     constituents
    1.28
     usual
    1.21
     latest
    1.21
     inability
    1.19
     ability
    1.17
     predecessor
    1.17
    Activations Density 1.344%

    No Known Activations