© 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. 37344
    Prev
    Next
    INDEX
    Explanations

    instances of uncertainty or hesitation in communication

    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
    481
    +0.15
    0.7%
    356
    +0.10
    0.5%
    565
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    356
    +0.15
    0.03
    501
    +0.10
    0.03
    135
    +0.09
    0.03
    Negative Logits
    SourceFile
    -0.88
    ULAR
    -0.81
    ãĤ¼ãĤ¦ãĤ¹
    -0.74
    pecially
    -0.71
    ENN
    -0.66
    MpServer
    -0.65
    arah
    -0.65
    grand
    -0.65
    oodle
    -0.64
    ige
    -0.64
    POSITIVE LOGITS
     unlike
    1.06
     beware
    0.91
     alas
    0.90
     there
    0.89
     contrary
    0.87
     despite
    0.87
     according
    0.86
     owing
    0.82
     neither
    0.80
     whereas
    0.80
    Activations Density 0.068%

    No Known Activations