© 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. 23262
    Prev
    Next
    INDEX
    Explanations

    topics or subjects that are the primary focus of discussion

    oai_token-act-pair · gpt-3.5-turbo

    key phrases indicating primary or main topics of discussion

    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
    etimes
    -0.81
     Leone
    -0.78
    ldom
    -0.75
    iron
    -0.75
    each
    -0.71
    romeda
    -0.71
    utics
    -0.70
    alus
    -0.69
    gemony
    -0.69
    ila
    -0.67
    POSITIVE LOGITS
    stay
    1.47
     culprit
    1.31
     reason
    1.29
     reasons
    1.17
     beneficiaries
    1.14
     beneficiary
    1.14
     obstacle
    1.14
     focus
    1.12
     objective
    1.12
     impetus
    1.11
    Activations Density 0.077%

    No Known Activations