© 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. 11713
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the word "spores" within the text

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and references to biological spores

    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
     precedence
    -0.72
     proportional
    -0.71
     connecting
    -0.70
     refreshing
    -0.69
     conduc
    -0.66
    uncture
    -0.66
     consent
    -0.65
    ccess
    -0.64
     resisting
    -0.64
     circum
    -0.63
    POSITIVE LOGITS
    dor
    2.12
    haus
    0.90
    esm
    0.82
    milo
    0.78
    eri
    0.76
    erk
    0.75
    osaurus
    0.75
    erest
    0.75
    SPONSORED
    0.75
    erd
    0.73
    Activations Density 0.001%

    No Known Activations