© 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. 1-RES-JB
    11. 23562
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    library
    -0.79
    Madison
    -0.73
     Dagger
    -0.72
     Cock
    -0.67
    EDIT
    -0.66
     Blink
    -0.64
     Cats
    -0.64
     Fiction
    -0.63
     Shiite
    -0.62
    rising
    -0.62
    POSITIVE LOGITS
     Mata
    0.89
    unia
    0.87
    fer
    0.82
    iversal
    0.82
    ÃŃa
    0.80
    acho
    0.79
     Gaal
    0.77
    orr
    0.77
    ijn
    0.76
    ilies
    0.74
    Activations Density 0.017%

    No Known Activations