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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10476
    Prev
    Next
    INDEX
    Explanations

    technical terms or proper nouns related to space exploration

    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
    137
    +0.11
    0.5%
    456
    +0.10
    0.5%
    489
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    137
    +0.11
    0.01
    527
    +0.10
    0.02
    487
    +0.10
    0.02
    Negative Logits
     guiActiveUnfocused
    -0.90
     relativity
    -0.75
    orage
    -0.72
    IFIED
    -0.68
    UGE
    -0.66
    etts
    -0.66
    ariat
    -0.63
    UME
    -0.63
    ieri
    -0.62
    ãģį
    -0.62
    POSITIVE LOGITS
    prus
    1.47
    cles
    1.46
    cling
    1.31
    clone
    1.20
    bers
    1.08
    cle
    1.05
    cled
    1.04
    pher
    1.04
    stic
    1.03
    cler
    0.96
    Activations Density 0.051%

    No Known Activations