© 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. 6-RES-JB
    11. 481
    Prev
    Next
    INDEX
    Explanations

    positive and negative test results

    oai_token-act-pair · gpt-3.5-turbo

    references to medical testing results, specifically related to positive and negative outcomes for various substances

    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
    ¬¼
    -0.77
    cape
    -0.76
    Nap
    -0.70
    skill
    -0.70
    pread
    -0.70
    isSpecialOrderable
    -0.69
    accompan
    -0.67
    scape
    -0.65
    OWS
    -0.64
    grad
    -0.63
    POSITIVE LOGITS
     Guilty
    0.77
     uranium
    0.75
     ATF
    0.74
    negative
    0.72
     urine
    0.71
    aye
    0.71
     unfit
    0.70
     antibodies
    0.70
    ysis
    0.69
    alde
    0.67
    Activations Density 0.071%

    No Known Activations