© 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. 16577
    Prev
    Next
    INDEX
    Explanations

    sequences of words that look like code snippets or commands

    oai_token-act-pair · gpt-3.5-turbo

    elements related to medical or scientific terminology

    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
     thereto
    -0.64
     to
    -0.62
    ĸļ
    -0.56
    forth
    -0.48
     interchange
    -0.47
     Unsure
    -0.44
    to
    -0.44
     obscurity
    -0.43
     sight
    -0.42
    isSpecialOrderable
    -0.42
    POSITIVE LOGITS
    anos
    0.53
    ONES
    0.50
    gre
    0.45
    lain
    0.44
    owan
    0.44
    OHN
    0.43
    inas
    0.43
    apeshifter
    0.43
     Leban
    0.42
    NVIDIA
    0.42
    Activations Density 1.032%

    No Known Activations