© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 844
    Prev
    Next
    INDEX
    Explanations

    American dollar amounts preceded by a currency symbol and followed by a unit of measurement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    165
    +0.12
    0.5%
    162
    +0.11
    0.5%
    158
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.12
    0.04
    193
    +0.11
    0.04
    165
    +0.10
    0.03
    Negative Logits
    ãĤ¡
    -0.68
     epidem
    -0.66
    aign
    -0.60
     Starr
    -0.59
    =#
    -0.59
    terday
    -0.59
    forth
    -0.58
     minds
    -0.58
    ATIONAL
    -0.58
     Epidem
    -0.57
    POSITIVE LOGITS
    AUD
    1.01
    -$
    0.96
    USD
    0.94
     USD
    0.89
     sterling
    0.83
     bribe
    0.82
     (£
    0.81
     cents
    0.78
     upkeep
    0.78
    each
    0.77
    Activations Density 0.201%

    No Known Activations