© 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. 37395
    Prev
    Next
    INDEX
    Explanations

    phrases related to levels, measurements, and assessments of various phenomena

    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
    447
    +0.18
    0.8%
    481
    +0.11
    0.5%
    459
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.18
    0.07
    288
    +0.11
    0.07
    341
    +0.10
    0.05
    Negative Logits
    ertain
    -0.59
    agog
    -0.58
    rums
    -0.55
    ãĥ£
    -0.54
    agen
    -0.53
    ãĥ©ãĥ³
    -0.52
    azeera
    -0.50
     spoon
    -0.50
    bert
    -0.50
    ead
    -0.49
    POSITIVE LOGITS
     destro
    0.81
     Azerb
    0.76
     rul
    0.74
     withd
    0.73
     confir
    0.69
     apiece
    0.68
     explan
    0.66
     altogether
    0.64
     redes
    0.63
     proport
    0.63
    Activations Density 0.413%

    No Known Activations