© 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 12288
    9. 8-RES_FS12288-JB
    11. 1460
    Prev
    Next
    INDEX
    Explanations

    words related to cryptocurrency and blockchain technology

    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
    503
    +0.15
    0.7%
    527
    +0.10
    0.5%
    300
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.15
    0.03
    503
    +0.10
    0.02
    300
    +0.10
    0.03
    Negative Logits
    ivities
    -0.84
    UAL
    -0.78
    yards
    -0.72
    Angelo
    -0.72
     Divinity
    -0.72
     Uriel
    -0.68
    âĸ¬
    -0.68
     Orient
    -0.66
     Painter
    -0.65
     guiActiveUnfocused
    -0.64
    POSITIVE LOGITS
    acter
    1.25
    edience
    1.17
    fusc
    1.15
    rien
    1.12
    ranch
    1.11
    acco
    1.10
    server
    1.09
    esity
    1.07
    edient
    1.06
    lique
    1.06
    Activations Density 0.048%

    No Known Activations