© 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. 7398
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical and archaeological information

    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
    572
    +0.12
    0.6%
    197
    +0.10
    0.5%
    66
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    197
    +0.12
    0.03
    460
    +0.10
    0.03
    72
    +0.10
    0.03
    Negative Logits
     welcome
    -0.67
    Kind
    -0.63
    CLASSIFIED
    -0.63
    CHAPTER
    -0.60
     yourselves
    -0.58
    Ô
    -0.57
    ACE
    -0.56
    kind
    -0.55
     torch
    -0.54
    ħĭ
    -0.54
    POSITIVE LOGITS
    addock
    0.76
    ativity
    0.70
    adish
    0.70
    staff
    0.69
    rained
    0.68
     that
    0.68
    psc
    0.66
    that
    0.65
    uggest
    0.65
    yip
    0.65
    Activations Density 0.204%

    No Known Activations