© 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. 41753
    Prev
    Next
    INDEX
    Explanations

    phrases related to uploading and downplaying situations or emotions

    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
    99
    +0.12
    0.6%
    526
    +0.12
    0.5%
    288
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.12
    0.01
    380
    +0.12
    0.01
    99
    +0.12
    0.01
    Negative Logits
    soDeliveryDate
    -0.77
     Dragonbound
    -0.76
    ãģ®éŃĶ
    -0.71
     Mistress
    -0.69
    BOOK
    -0.69
    ãģ¦
    -0.67
     Electronic
    -0.65
     Fiscal
    -0.64
     Slate
    -0.63
     Goo
    -0.63
    POSITIVE LOGITS
    ifted
    1.37
    ifting
    1.33
    ift
    1.25
    atters
    1.17
    oved
    1.16
    itud
    1.11
    ifts
    1.10
    ongs
    1.09
    iever
    1.08
    ittle
    1.07
    Activations Density 0.005%

    No Known Activations