© 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. 7-RES-JB
    11. 9748
    Prev
    Next
    INDEX
    Explanations

    Javascript object properties and values

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.72
     conclud
    -0.70
    iasis
    -0.68
    ega
    -0.68
    itational
    -0.67
    iners
    -0.66
    ?'"
    -0.65
    Thirty
    -0.63
    ECA
    -0.62
    inson
    -0.61
    POSITIVE LOGITS
     etc
    0.97
    ioch
    0.80
     /*
    0.78
     len
    0.73
     //
    0.73
     linen
    0.72
     respectively
    0.71
     sizeof
    0.71
     uint
    0.70
     lambda
    0.70
    Activations Density 0.083%

    No Known Activations