© 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. 10-RES-JB
    11. 7752
    Prev
    Next
    INDEX
    Explanations

    phrases ending in a particular punctuation mark

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods indicating the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metic
    -0.66
    anmar
    -0.58
     IST
    -0.54
    IAS
    -0.52
    opter
    -0.52
     artif
    -0.52
     Kyoto
    -0.51
     NYT
    -0.51
     FB
    -0.51
     Canaver
    -0.50
    POSITIVE LOGITS
    ↵
    0.97
    SPONSORED
    0.82
    <|endoftext|>
    0.76
    gard
    0.72
    ↵↵
    0.66
    ppard
    0.66
    0.57
    Lt
    0.55
    ii
    0.53
     (*
    0.53
    Activations Density 0.182%

    No Known Activations