© 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. 16366
    Prev
    Next
    INDEX
    Explanations

    related to physical objects or materials in certain conditions, such as seams in a bag or maintenance of equipment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to maintenance and structural integrity

    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
    ivalent
    -0.73
     accrued
    -0.72
     contrace
    -0.70
     applicable
    -0.69
    conom
    -0.69
    hips
    -0.67
     constitu
    -0.67
    ividual
    -0.65
    ustomed
    -0.63
     liking
    -0.63
    POSITIVE LOGITS
     Mole
    0.73
    acular
    0.67
    ooo
    0.64
     Malfoy
    0.63
    OPLE
    0.62
    060
    0.62
    024
    0.61
    6666
    0.61
    OO
    0.60
    urred
    0.60
    Activations Density 0.001%

    No Known Activations