© 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. 37220
    Prev
    Next
    INDEX
    Explanations

    references to technological advancements and medical conditions

    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
    711
    +0.12
    0.6%
    234
    +0.10
    0.5%
    109
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    711
    +0.12
    0.03
    686
    +0.10
    0.03
    109
    +0.10
    0.04
    Negative Logits
    MSN
    -0.66
    DK
    -0.65
    HAHAHAHA
    -0.64
    soDeliveryDate
    -0.64
     Patreon
    -0.62
    Ô
    -0.62
    Dialogue
    -0.61
     ALP
    -0.61
    ONSORED
    -0.60
     Tome
    -0.60
    POSITIVE LOGITS
    })
    0.98
    *)
    0.97
    ?),
    0.96
    )—
    0.90
     })
    0.88
    ?).
    0.85
    "),
    0.85
    +)
    0.84
    ?)
    0.83
    )?
    0.82
    Activations Density 0.648%

    No Known Activations