© 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. 18845
    Prev
    Next
    INDEX
    Explanations

    HTML tags indicating the closure of various elements

    oai_token-act-pair · gpt-3.5-turbo

    HTML tags and structural elements

    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
     nodd
    -0.84
     vulner
    -0.81
     Bake
    -0.77
     Cumber
    -0.77
     satell
    -0.76
     demol
    -0.75
     conclud
    -0.74
     crochet
    -0.73
     hemor
    -0.71
     Gron
    -0.70
    POSITIVE LOGITS
    span
    1.31
    font
    1.31
    div
    1.30
    td
    1.28
    url
    1.20
    href
    1.18
    center
    1.17
    iframe
    1.13
    manac
    1.09
    figure
    1.06
    Activations Density 0.011%

    No Known Activations