© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 11266
    Prev
    Next
    INDEX
    Explanations

    computer programming-related terms and expressions

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and references to digital content or functions

    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
     reconc
    -0.73
     traged
    -0.64
     corpor
    -0.64
     pse
    -0.62
     mathemat
    -0.61
     Garner
    -0.60
     metic
    -0.59
     civilian
    -0.57
     RAND
    -0.56
     tranquil
    -0.55
    POSITIVE LOGITS
    )
    1.56
    )'
    1.25
    ),
    1.15
    )...
    1.15
    )(
    1.12
    )\
    1.10
    )"
    1.08
    )!
    1.08
    )/
    1.07
    )=
    1.07
    Activations Density 0.107%

    No Known Activations