© 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 24576
    9. 8-RES_FS24576-JB
    11. 18796
    Prev
    Next
    INDEX
    Explanations

    words related to criticism and disapproval

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    653
    +0.11
    0.5%
    214
    +0.10
    0.4%
    128
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    653
    +0.11
    0.02
    214
    +0.10
    0.02
    163
    +0.10
    0.02
    Negative Logits
    lihood
    -0.91
    EMENT
    -0.68
    ropolitan
    -0.67
     Polo
    -0.66
    é¾įå
    -0.66
    olean
    -0.65
    DragonMagazine
    -0.64
     Masters
    -0.64
     Rath
    -0.63
    姫
    -0.63
    POSITIVE LOGITS
    umbs
    1.24
    umbled
    1.23
    umb
    1.22
    umbles
    1.21
    anked
    1.09
    ump
    1.08
    ickets
    1.05
    amping
    1.03
    usted
    1.01
    umbling
    1.01
    Activations Density 0.009%

    No Known Activations