© 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. 11-RES-JB
    11. 18683
    Prev
    Next
    INDEX
    Explanations

    statements expressing a sense of urgency or finality

    oai_token-act-pair · gpt-3.5-turbo

    instances of periods marking 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 @ 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
     predec
    -0.58
    emaker
    -0.56
     advoc
    -0.55
     designated
    -0.55
     credential
    -0.54
    ELD
    -0.53
    lier
    -0.52
     claimant
    -0.50
     contested
    -0.49
     nationally
    -0.48
    POSITIVE LOGITS
     ;)
    1.03
     :)
    1.01
     :(
    0.93
     Seriously
    0.93
     Anyway
    0.92
     Sorry
    0.88
     Yeah
    0.88
     lol
    0.87
     Alright
    0.87
     Been
    0.86
    Activations Density 0.322%

    No Known Activations