© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23895
    Prev
    Next
    INDEX
    Explanations

    programming concepts and elements, particularly related to defining roles, handling errors, and representing structures in languages like Ruby and Python

    oai_token-act-pair · gpt-4o-miniTriggered 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
    447
    +0.13
    0.6%
    255
    +0.12
    0.6%
    384
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.04
    255
    +0.12
    0.04
    345
    +0.11
    0.04
    Negative Logits
     NTS
    -0.74
     TBA
    -0.71
    ][/
    -0.66
     sweat
    -0.64
     Hayden
    -0.64
     immersion
    -0.63
     puff
    -0.61
     liv
    -0.61
     daytime
    -0.59
     HG
    -0.59
    POSITIVE LOGITS
    ()
    1.41
    ().
    1.38
    (),
    1.34
    Async
    1.18
    ():
    1.09
    ())
    1.02
    Property
    0.99
    Args
    0.99
    Array
    0.98
    String
    0.98
    Activations Density 0.188%

    No Known Activations