© 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. 8-RES-JB
    11. 4161
    Prev
    Next
    INDEX
    Explanations

    phrases related to vision and hearing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to vision and visual impairment

    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
    atern
    -0.70
     Git
    -0.68
     Meal
    -0.67
    sale
    -0.67
    aternal
    -0.67
     Bundy
    -0.66
     Slaughter
    -0.66
    aji
    -0.65
     OPEC
    -0.65
    ivari
    -0.63
    POSITIVE LOGITS
     goggles
    1.13
     impaired
    1.12
    ight
    1.01
     impairment
    0.97
     cones
    0.95
     illusions
    0.95
    seeing
    0.90
     cone
    0.88
    blind
    0.88
     deprivation
    0.86
    Activations Density 0.171%

    No Known Activations