© 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. 0-RES-JB
    11. 20445
    Prev
    Next
    INDEX
    Explanations

    words related to the term "auts"

    oai_token-act-pair · gpt-3.5-turbo

    references to fictional or gaming characters, particularly those associated with space exploration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opa
    -0.72
    photo
    -0.71
     marg
    -0.70
    iam
    -0.70
     quantitative
    -0.69
    adjust
    -0.68
    blogs
    -0.67
     appraisal
    -0.67
     Sem
    -0.64
    EPA
    -0.64
    POSITIVE LOGITS
    auts
    1.97
    ega
    1.74
    EGA
    1.43
    sov
    1.36
    pload
    1.35
    etus
    1.13
    rift
    1.12
    seless
    1.07
    nen
    1.07
    eering
    1.03
    Activations Density 0.053%

    No Known Activations