© 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. 1532
    Prev
    Next
    INDEX
    Explanations

    terms related to large corporations or businesses

    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
    161
    +0.10
    0.5%
    48
    +0.10
    0.5%
    508
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.10
    0.01
    161
    +0.10
    0.01
    22
    +0.10
    0.01
    Negative Logits
    ãģį
    -0.76
     resolve
    -0.68
    âķIJâķIJ
    -0.67
     Sense
    -0.66
     Paradox
    -0.66
    UCT
    -0.65
    LECT
    -0.64
    ÙIJ
    -0.63
     Continued
    -0.62
    velt
    -0.61
    POSITIVE LOGITS
    abyte
    1.42
    abytes
    1.34
    atron
    1.20
    apixel
    1.19
    awatts
    1.13
    aton
    1.06
    apolis
    0.99
    acity
    0.99
    atis
    0.98
    enary
    0.97
    Activations Density 0.010%

    No Known Activations