© 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. 21484
    Prev
    Next
    INDEX
    Explanations

    phrases indicating imminent or current actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating statements of fact or opinion

    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
    uman
    -0.48
    isal
    -0.48
    uesday
    -0.46
     Downs
    -0.41
    osi
    -0.41
    _>
    -0.40
    uko
    -0.40
    :'
    -0.39
    Ey
    -0.39
    oft
    -0.39
    POSITIVE LOGITS
     to
    0.91
    BuyableInstoreAndOnline
    0.62
    senal
    0.60
     TO
    0.55
    To
    0.54
    to
    0.52
    ThumbnailImage
    0.52
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    0.51
     thereto
    0.50
    StreamerBot
    0.49
    Activations Density 0.824%

    No Known Activations