© 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. 20386
    Prev
    Next
    INDEX
    Explanations

    words related to different choices or alternatives

    oai_token-act-pair · gpt-3.5-turbo

    various options and alternatives available in different contexts

    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
    OV
    -0.70
    onel
    -0.64
    Writ
    -0.63
    Untitled
    -0.62
    oned
    -0.61
    adelphia
    -0.60
    Die
    -0.60
    enged
    -0.59
    athon
    -0.58
    ograph
    -0.57
    POSITIVE LOGITS
    cale
    1.17
    etting
    1.14
    paces
    1.14
    pring
    1.13
    pace
    1.13
     abound
    1.10
    ensical
    1.04
    ourcing
    1.01
    ystem
    1.00
    olutions
    0.94
    Activations Density 0.291%

    No Known Activations