© 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. 2-RES-JB
    11. 17279
    Prev
    Next
    INDEX
    Explanations

    past medical conditions or health-related history

    oai_token-act-pair · gpt-3.5-turbo

    references to past medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chains
    -0.73
    Å
    -0.68
     encamp
    -0.64
     grun
    -0.63
     salts
    -0.63
     Kraken
    -0.61
     bras
    -0.60
    á¹
    -0.59
    iott
    -0.59
    ocamp
    -0.58
    POSITIVE LOGITS
    ilver
    0.70
    avorite
    0.68
    dial
    0.67
    tenance
    0.66
    gallery
    0.65
    lic
    0.65
    series
    0.64
     Lens
    0.64
    lict
    0.64
    finished
    0.64
    Activations Density 0.000%

    No Known Activations