© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 7887
    Prev
    Next
    INDEX
    Explanations

    warnings or disclaimers mentioning specific intended audiences or precautions

    oai_token-act-pair · gpt-3.5-turbo

    warnings and disclaimers related to product usage and content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suddenly
    -0.59
     rupt
    -0.58
    armac
    -0.56
     devast
    -0.56
     intensified
    -0.56
    ?),
    -0.55
    ?",
    -0.54
     destabil
    -0.54
     later
    -0.53
     yawn
    -0.52
    POSITIVE LOGITS
     unless
    1.06
     ONLY
    1.02
    unless
    0.96
     Please
    0.92
     :-)
    0.89
     :)
    0.87
    <|endoftext|>
    0.86
     except
    0.86
    .-
    0.86
     ;)
    0.85
    Activations Density 0.471%

    No Known Activations