© 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. 1201
    Prev
    Next
    INDEX
    Explanations

    short phrases or words in Spanish that are related to various topics or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances or references to a specific item or subject

    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
    advertisement
    -0.75
     bullies
    -0.72
    Shock
    -0.71
    SPONSORED
    -0.70
    Background
    -0.69
     bribery
    -0.67
    -$
    -0.66
    Strength
    -0.64
     footprints
    -0.63
     tariffs
    -0.63
    POSITIVE LOGITS
    ño
    1.07
    ñ
    1.02
    gypt
    0.88
     los
    0.87
    lde
    0.84
    stem
    0.84
    hab
    0.84
    vez
    0.83
    ige
    0.83
    ç
    0.83
    Activations Density 0.068%

    No Known Activations