© 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. 20198
    Prev
    Next
    INDEX
    Explanations

    phrases referring to a small quantity or group of something

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "a handful of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    abolic
    -0.80
    mediate
    -0.71
    cel
    -0.71
    abol
    -0.68
    atro
    -0.67
    agnar
    -0.65
    flu
    -0.63
    ondo
    -0.63
    agate
    -0.63
    ogens
    -0.62
    POSITIVE LOGITS
     handful
    0.94
     dozen
    0.82
    een
    0.80
    eenth
    0.80
     newcom
    0.79
    ĸļ
    0.77
    ï¸ı
    0.77
    uously
    0.74
    hetti
    0.69
    ãĤ¼ãĤ¦ãĤ¹
    0.68
    Activations Density 0.005%

    No Known Activations