© 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 24576
    9. 8-RES_FS24576-JB
    11. 19336
    Prev
    Next
    INDEX
    Explanations

    information related to memory and technical details

    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
    481
    +0.16
    0.7%
    485
    +0.11
    0.5%
    630
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.07
    225
    +0.11
    0.06
    575
    +0.10
    0.06
    Negative Logits
    »Ĵ
    -0.82
    ciating
    -0.81
    ¿½
    -0.74
    APTER
    -0.74
    Īè
    -0.73
    vous
    -0.72
     referen
    -0.72
    Ô
    -0.68
    ÑĤ
    -0.68
    اÙĦ
    -0.67
    POSITIVE LOGITS
    imus
    0.73
    ousel
    0.69
    ause
    0.64
    ipes
    0.64
    amph
    0.61
     Extras
    0.60
    ets
    0.59
    riers
    0.58
     selector
    0.58
     DVD
    0.57
    Activations Density 0.393%

    No Known Activations