© 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. 9092
    Prev
    Next
    INDEX
    Explanations

    references to a particular person named Uma

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly names with the substring "uma"

    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
    lean
    -0.66
     Boolean
    -0.66
    ICLE
    -0.65
    neath
    -0.65
    tons
    -0.65
     Canadians
    -0.64
    bidden
    -0.59
    ician
    -0.59
    Trend
    -0.58
    Else
    -0.58
    POSITIVE LOGITS
    uma
    1.41
    ppa
    0.96
    ascus
    0.89
    velength
    0.84
    isoft
    0.80
    unta
    0.77
    iba
    0.76
    uli
    0.74
    asar
    0.74
    oresc
    0.72
    Activations Density 0.007%

    No Known Activations