© 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. 21119
    Prev
    Next
    INDEX
    Explanations

    proper nouns and titles

    oai_token-act-pair · gpt-3.5-turbo

    references to photography and image sources

    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
     bonding
    -0.79
     fel
    -0.77
     bending
    -0.69
     dur
    -0.69
     Levin
    -0.68
    raham
    -0.68
     Dy
    -0.68
     monop
    -0.67
     Shel
    -0.67
    zees
    -0.66
    POSITIVE LOGITS
    EPA
    1.13
    Reuters
    1.09
    Getty
    1.06
    UTERS
    1.04
    AP
    1.03
    Streamer
    1.00
    AFP
    0.98
    Cooldown
    0.92
    ForgeModLoader
    0.89
    NASA
    0.87
    Activations Density 0.111%

    No Known Activations