© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 5288
    Prev
    Next
    INDEX
    Explanations

    mentions of incompleteness or partiality

    oai_token-act-pair · gpt-3.5-turbo

    references to partiality or incomplete aspects of concepts or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Trend
    -1.02
    ħĭ
    -0.88
    åĤ
    -0.83
    ORGE
    -0.80
    ¯¯
    -0.79
    eers
    -0.78
    ERG
    -0.73
     Trend
    -0.72
     Royale
    -0.69
    orge
    -0.68
    POSITIVE LOGITS
     partial
    1.02
     eclipse
    0.97
    ity
    0.85
    iple
    0.81
     pane
    0.77
     pard
    0.76
     Partial
    0.76
     collateral
    0.74
     spoil
    0.74
     agon
    0.72
    Activations Density 0.004%

    No Known Activations