© 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. 22477
    Prev
    Next
    INDEX
    Explanations

    references to physical attributes or features

    oai_token-act-pair · gpt-3.5-turbo

    references to specific parts or components in a description

    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
    SHARE
    -0.95
    æµ
    -0.75
    minent
    -0.75
    arcity
    -0.73
    Malley
    -0.72
    abilities
    -0.72
    Jim
    -0.72
     Alone
    -0.71
    Energy
    -0.71
    PD
    -0.71
    POSITIVE LOGITS
     underside
    1.64
     edges
    1.59
     corners
    1.49
     sides
    1.49
     circumference
    1.42
     bottom
    1.35
     widest
    1.35
     outer
    1.32
     spine
    1.25
     forehead
    1.25
    Activations Density 0.184%

    No Known Activations