© 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. 8-RES-JB
    11. 1916
    Prev
    Next
    INDEX
    Explanations

    decimal numbers with the specific format X.X

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to measurements and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elia
    -0.68
    swick
    -0.66
    strings
    -0.63
    hunt
    -0.61
    dump
    -0.57
     Heist
    -0.56
    stru
    -0.55
    eded
    -0.54
    cod
    -0.54
     Humph
    -0.53
    POSITIVE LOGITS
     lakh
    0.93
    Thirty
    0.92
     million
    0.89
     ILCS
    0.84
    MN
    0.81
    0000
    0.80
     crore
    0.80
    mL
    0.79
    GHz
    0.78
     billion
    0.78
    Activations Density 0.045%

    No Known Activations