© 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. 37180
    Prev
    Next
    INDEX
    Explanations

    occurrences of the substring "ne" within various contexts

    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
    57
    +0.14
    0.6%
    153
    +0.12
    0.5%
    99
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.14
    0.01
    439
    +0.12
    0.01
    153
    +0.10
    0.01
    Negative Logits
    hips
    -0.85
    loo
    -0.75
    ENSE
    -0.72
    AGES
    -0.72
    ãĥ¼ãĥĨãĤ£
    -0.64
    DOWN
    -0.64
     ecstasy
    -0.62
    Ranked
    -0.61
     bearer
    -0.61
     lockout
    -0.61
    POSITIVE LOGITS
    verend
    1.17
    arest
    1.13
    olithic
    1.01
    pher
    0.99
    ccess
    0.97
    uter
    0.97
    braska
    0.93
    uron
    0.91
    arthed
    0.91
    erd
    0.89
    Activations Density 0.006%

    No Known Activations