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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 24375
    Prev
    Next
    INDEX
    Explanations

    phrases related to investigations or probing of certain matters or issues

    oai_token-act-pair · gpt-3.5-turbo

    references to investigations or inquiries into various matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cil
    -0.92
    haps
    -0.77
    SPONSORED
    -0.76
    wart
    -0.73
    ranged
    -0.72
    nir
    -0.71
    isSpecialOrderable
    -0.71
    icia
    -0.69
    âĿ
    -0.68
    anguage
    -0.67
    POSITIVE LOGITS
     feasibility
    1.12
     legality
    1.09
     possibility
    1.09
     discrepancy
    0.99
     whereabouts
    0.99
     adequ
    0.99
     situation
    0.98
     validity
    0.98
     disappearance
    0.97
     workings
    0.94
    Activations Density 0.285%

    No Known Activations