© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 26528
    Prev
    Next
    INDEX
    Explanations

    phrases related to revising or negating previous statements or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    372
    +0.13
    0.6%
    143
    +0.11
    0.5%
    641
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    143
    +0.13
    0.02
    372
    +0.11
    0.02
    641
    +0.10
    0.02
    Negative Logits
    entric
    -0.86
    risome
    -0.70
    uyomi
    -0.68
     viz
    -0.61
    inational
    -0.60
    ities
    -0.60
    orp
    -0.60
    uria
    -0.60
    terday
    -0.59
    æ©Ł
    -0.59
    POSITIVE LOGITS
    track
    1.23
    stab
    1.13
    dated
    1.07
    packs
    1.05
    ped
    1.01
    loaded
    0.98
    tracking
    0.97
    side
    0.97
    strap
    0.94
    pack
    0.93
    Activations Density 0.015%

    No Known Activations