© 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. 9382
    Prev
    Next
    INDEX
    Explanations

    information about newsletters or magazines and their subscription options

    oai_token-act-pair · gpt-3.5-turbo

    references to issues, articles, and subscription-related content

    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
    rounded
    -0.58
    estern
    -0.57
    imates
    -0.55
    places
    -0.54
    ey
    -0.53
    graded
    -0.53
    agog
    -0.52
     recess
    -0.50
    place
    -0.49
    rophe
    -0.49
    POSITIVE LOGITS
    Initialized
    0.53
    DragonMagazine
    0.52
     Gutenberg
    0.50
     Patron
    0.49
    ilty
    0.49
    ulf
    0.48
    çİĭ
    0.48
    powder
    0.48
    arate
    0.48
    Unix
    0.47
    Activations Density 0.094%

    No Known Activations