© 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. 6-RES-JB
    11. 9827
    Prev
    Next
    INDEX
    Explanations

    instances where the document mentions a requirement or necessity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" indicating purpose or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     glances
    -0.65
    soDeliveryDate
    -0.65
    ivated
    -0.63
     Laksh
    -0.63
    atta
    -0.63
    Written
    -0.62
     Lines
    -0.62
    Privacy
    -0.62
     Fired
    -0.62
     Porn
    -0.61
    POSITIVE LOGITS
     satisfy
    1.35
     compensate
    1.29
     justify
    1.25
     ensure
    1.24
     achieve
    1.22
     solve
    1.20
     accomplish
    1.19
     accommodate
    1.19
     overcome
    1.18
     prove
    1.18
    Activations Density 0.208%

    No Known Activations