© 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. 14540
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically periods

    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
     advis
    -0.71
     enthusi
    -0.70
     cod
    -0.68
     attacker
    -0.67
     volunte
    -0.66
     induct
    -0.65
     rall
    -0.65
     exclus
    -0.65
     veter
    -0.65
     collectors
    -0.64
    POSITIVE LOGITS
    jpg
    0.84
    blogspot
    0.80
    esp
    0.79
    html
    0.77
    icio
    0.77
    htm
    0.77
    dll
    0.76
     [+
    0.75
    sbm
    0.72
    prototype
    0.71
    Activations Density 0.696%

    No Known Activations