© 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. 6996
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events happening or being done by individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    concrete nouns and specific terms indicating physical locations or statuses

    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
     ON
    -0.67
     glim
    -0.61
    On
    -0.59
     On
    -0.57
    rescent
    -0.57
    ategory
    -0.57
    opia
    -0.54
    on
    -0.53
    iton
    -0.52
     DRAG
    -0.52
    POSITIVE LOGITS
     occasions
    1.20
     basis
    1.20
     behalf
    1.12
     occasion
    0.99
     doorstep
    0.91
     periphery
    0.87
     verge
    0.87
     pedest
    0.87
     side
    0.86
     bandwagon
    0.84
    Activations Density 0.483%

    No Known Activations