Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 7649
    Prev
    Next
    INDEX
    Explanations

    words related to achieving notable accomplishments or victories

    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
    683
    +0.13
    0.6%
    438
    +0.12
    0.6%
    420
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.13
    0.02
    26
    +0.12
    0.02
    276
    +0.12
    0.02
    Negative Logits
    PsyNetMessage
    -0.82
    EMBER
    -0.74
    ãĤ£
    -0.73
    oding
    -0.71
    ãĥ´ãĤ¡
    -0.69
    BuyableInstoreAndOnline
    -0.69
     unfocusedRange
    -0.67
    ãģ®å
    -0.66
     ILCS
    -0.66
    ONT
    -0.64
    POSITIVE LOGITS
    erman
    1.15
    ery
    1.10
    ering
    1.09
    leness
    1.06
    ett
    1.04
    ety
    1.03
    etts
    0.99
    hoff
    0.99
    eters
    0.98
    nesses
    0.97
    Activations Density 0.030%

    No Known Activations