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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4110
    Prev
    Next
    INDEX
    Explanations

    locations and events

    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
    373
    +0.20
    1.0%
    680
    +0.11
    0.5%
    67
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.20
    0.09
    362
    +0.11
    0.08
    58
    +0.10
    0.04
    Negative Logits
    !.
    -0.81
    `.
    -0.78
    '.
    -0.77
    %.
    -0.76
     âĵĺ
    -0.74
    +.
    -0.74
    ''.
    -0.74
    .
    -0.72
    .�
    -0.71
    .:
    -0.71
    POSITIVE LOGITS
    )}
    0.52
     conventions
    0.51
     foregoing
    0.50
     slightest
    0.50
     constraints
    0.49
    urances
    0.49
     stimulus
    0.49
     )]
    0.47
    >)
    0.47
    *)
    0.47
    Activations Density 1.480%

    No Known Activations