© 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. 20477
    Prev
    Next
    INDEX
    Explanations

    a specific word related to medical conditions, spelled in different variations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring 'ir'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     untreated
    -0.67
    Ĥª
    -0.65
     Wolver
    -0.63
    er
    -0.61
    ĨĴ
    -0.59
    legates
    -0.59
    ļé
    -0.58
     warrant
    -0.58
    alter
    -0.57
     clue
    -0.57
    POSITIVE LOGITS
    vana
    1.33
    rha
    1.14
    andom
    1.06
    mingham
    0.99
    oux
    0.97
    ror
    0.94
    acial
    0.91
    cles
    0.91
    ROR
    0.89
    abbit
    0.89
    Activations Density 0.028%

    No Known Activations