© 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. 12851
    Prev
    Next
    INDEX
    Explanations

    references to hats

    oai_token-act-pair · gpt-3.5-turbo

    references to hats

    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
    theless
    -0.73
     MSM
    -0.63
     Integ
    -0.63
    IVES
    -0.62
     Impossible
    -0.60
     UNIVERS
    -0.60
     Gamma
    -0.59
    IV
    -0.58
    houn
    -0.57
     Bakr
    -0.57
    POSITIVE LOGITS
    chet
    1.80
    chery
    1.52
    ches
    1.28
    cher
    1.16
    glers
    1.10
    emark
    1.02
    ched
    1.00
    che
    0.99
    eless
    0.99
     brim
    0.95
    Activations Density 0.031%

    No Known Activations