© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-RES-JB
    11. 18460
    Prev
    Next
    INDEX
    Explanations

    terms related to alternative spellings or variations of names

    oai_token-act-pair · gpt-3.5-turbo

    names, particularly those with variations or alternative spellings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incentives
    -0.74
     healthcare
    -0.72
     incentiv
    -0.72
     constrained
    -0.71
     biases
    -0.71
     takeaway
    -0.70
     biomedical
    -0.69
     coerc
    -0.69
     conventions
    -0.68
     sampling
    -0.68
    POSITIVE LOGITS
    XXXX
    0.90
    XXX
    0.88
    Äĵ
    0.87
    xxxx
    0.86
    idae
    0.85
    hyde
    0.85
    -.
    0.84
    É
    0.84
    zee
    0.82
     Doe
    0.82
    Activations Density 0.407%

    No Known Activations