© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13780
    Prev
    Next
    INDEX
    Explanations

    descriptions of surveys or questionnaires being filled out

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating research methodologies or data collection processes

    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
     clearance
    -0.62
    efe
    -0.62
    Nonetheless
    -0.59
    士
    -0.59
    inventoryQuantity
    -0.58
    azeera
    -0.58
    Nevertheless
    -0.57
     exceeds
    -0.57
    orgetown
    -0.56
    dad
    -0.56
    POSITIVE LOGITS
     randomly
    1.06
     simulated
    0.83
     brainstorm
    0.81
     hypothetical
    0.77
     quiz
    0.76
     sketches
    0.76
     simulate
    0.75
     randomized
    0.75
     fictional
    0.75
     narr
    0.74
    Activations Density 1.053%

    No Known Activations