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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7996
    Prev
    Next
    INDEX
    Explanations

    statements and questions ending in a specific punctuation mark

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases ending with a period

    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
     corrid
    -0.67
     predec
    -0.63
     metic
    -0.62
     mosqu
    -0.61
     challeng
    -0.60
    ãĥ¼ãĥĨ
    -0.59
     redes
    -0.58
    emaker
    -0.56
    iber
    -0.55
    aga
    -0.55
    POSITIVE LOGITS
     Besides
    0.74
     Flavoring
    0.73
     Secondly
    0.72
     However
    0.71
     They
    0.71
     Specifically
    0.70
     It
    0.69
    tumblr
    0.68
     Since
    0.68
     Additionally
    0.67
    Activations Density 0.995%

    No Known Activations