© 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 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. 20789
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating a high degree of impact or importance

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating the severity or intensity of challenges or opposition

    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
    ilk
    -0.93
    ©¶æ
    -0.77
    hander
    -0.75
    roma
    -0.74
    handle
    -0.71
    ologue
    -0.70
    ramid
    -0.70
    hyde
    -0.69
    athon
    -0.69
    tick
    -0.68
    POSITIVE LOGITS
     amounts
    1.39
     quantities
    1.10
     indications
    1.02
     discrepancies
    1.01
     similarities
    1.00
     sums
    1.00
     scrutiny
    0.97
     parallels
    0.97
     comparisons
    0.97
     reductions
    0.96
    Activations Density 0.295%

    No Known Activations