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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 11485
    Prev
    Next
    INDEX
    Explanations

    peculiar patterns of symbols and words, possibly indicating a specific code or encryption

    oai_token-act-pair · gpt-3.5-turbo

    fragments of text expressing strong emotions or personal sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Partition Features Layer 8 GPT2 Small
    " token" vs "Token"

    No Comments

    Negative Logits
     covenant
    -0.81
     bracket
    -0.80
     raft
    -0.79
     licensing
    -0.78
     bailout
    -0.77
     previously
    -0.77
     camp
    -0.77
     carrier
    -0.76
     bloc
    -0.76
     favor
    -0.75
    POSITIVE LOGITS
    Only
    1.47
    Nothing
    1.46
    Where
    1.43
    If
    1.42
    Finally
    1.41
    And
    1.40
    Put
    1.38
    Anything
    1.37
    Poor
    1.37
    Whether
    1.37
    Activations Density 0.360%

    No Known Activations