© 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. 9-RES-JB
    11. 15383
    Prev
    Next
    INDEX
    Explanations

    information about the application or use of pesticides on crops

    oai_token-act-pair · gpt-3.5-turbo

    information related to agricultural practices and insecticides

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REDACTED
    -0.64
     Volcano
    -0.60
    çīĪ
    -0.57
    ''.
    -0.57
    anooga
    -0.57
    ?".
    -0.55
    ãĤ«
    -0.54
     Osw
    -0.53
     Verse
    -0.52
    uana
    -0.52
    POSITIVE LOGITS
     differently
    0.92
     themselves
    0.88
    often
    0.84
     whereas
    0.84
     inconsist
    0.79
     seldom
    0.77
     excessively
    0.76
     regardless
    0.76
     rarely
    0.76
     irrespective
    0.76
    Activations Density 1.377%

    No Known Activations