© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18587
    Prev
    Next
    INDEX
    Explanations

    locations or positions within an object or structure, typically relating to the top and bottom

    oai_token-act-pair · gpt-3.5-turbo

    references to the top and bottom positions in various contexts

    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
    istani
    -0.77
    yssey
    -0.76
    edIn
    -0.68
    MQ
    -0.67
    issance
    -0.65
     Tycoon
    -0.61
     Parenthood
    -0.60
     Talks
    -0.59
     Outbreak
    -0.58
     Apocalypse
    -0.57
    POSITIVE LOGITS
     thereof
    1.26
     of
    1.18
    most
    1.07
     edges
    1.05
     surfaces
    1.02
     edge
    0.99
     surface
    0.99
     portion
    0.97
     halves
    0.95
    boards
    0.94
    Activations Density 0.134%

    No Known Activations