© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 45452
    Prev
    Next
    INDEX
    Explanations

    references to gaming and video game experiences

    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
    481
    +0.22
    1.0%
    401
    +0.13
    0.6%
    581
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    39
    +0.22
    0.04
    401
    +0.13
    0.04
    762
    +0.10
    0.05
    Negative Logits
    ahime
    -0.76
    uers
    -0.62
    ¿½
    -0.61
    bral
    -0.61
     negotiators
    -0.60
    emn
    -0.60
    adr
    -0.58
     Omaha
    -0.57
     nep
    -0.56
    orst
    -0.55
    POSITIVE LOGITS
     except
    1.33
     imaginable
    1.22
     whatsoever
    1.17
    except
    1.05
    soever
    0.99
     including
    0.87
     besides
    0.79
     irrespective
    0.79
     regardless
    0.78
     MUST
    0.78
    Activations Density 0.253%

    No Known Activations