© 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. 10-RES-JB
    11. 21440
    Prev
    Next
    INDEX
    Explanations

    words related to specific situations or locations

    oai_token-act-pair · gpt-3.5-turbo

    key nouns that indicate central themes or contexts in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desks
    -0.68
     asteroids
    -0.65
     parties
    -0.61
     ceilings
    -0.61
     Roof
    -0.60
     CLR
    -0.60
     Doors
    -0.60
    asters
    -0.59
     Sections
    -0.59
    tails
    -0.59
    POSITIVE LOGITS
    cture
    0.84
    piece
    0.73
    iece
    0.70
    undrum
    0.68
    stros
    0.67
    oster
    0.67
     cycle
    0.66
    cule
    0.66
     sorely
    0.66
    claimer
    0.65
    Activations Density 0.241%

    No Known Activations