© 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. 11971
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or possibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing possibility or conditional statements

    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
    Materials
    -0.79
    ulously
    -0.68
    lier
    -0.67
    venture
    -0.64
    aneous
    -0.62
    âĵĺ
    -0.62
    icial
    -0.61
    ieves
    -0.61
    ailable
    -0.59
    foreseen
    -0.58
    POSITIVE LOGITS
    bes
    0.92
    hap
    0.82
    adian
    0.79
     exagger
    0.74
    haps
    0.73
     someday
    0.71
     herald
    0.70
     disagree
    0.67
    umph
    0.67
     incent
    0.66
    Activations Density 0.106%

    No Known Activations