© 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. 20343
    Prev
    Next
    INDEX
    Explanations

    the term "slew" used in various contexts referring to a large quantity of items

    oai_token-act-pair · gpt-3.5-turbo
    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
     harmony
    -0.64
     Matter
    -0.61
     separation
    -0.59
     interval
    -0.56
     guts
    -0.53
     equival
    -0.53
    oyer
    -0.53
     coordinates
    -0.52
     spores
    -0.50
     streng
    -0.50
    POSITIVE LOGITS
     of
    0.94
    dozen
    0.93
     dozen
    0.74
    alions
    0.73
    ij
    0.73
    eenth
    0.72
     Of
    0.71
    icularly
    0.69
    Of
    0.68
    assi
    0.68
    Activations Density 0.102%

    No Known Activations