© 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. 8961
    Prev
    Next
    INDEX
    Explanations

    information-related keywords and references

    oai_token-act-pair · gpt-3.5-turbo

    references to information and sources in the text

    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
    theless
    -0.77
     unexplained
    -0.67
     contraceptive
    -0.65
    loo
    -0.65
     Quarterly
    -0.64
     contraceptives
    -0.63
     Antarctic
    -0.63
    hani
    -0.61
     charism
    -0.60
     mandate
    -0.60
    POSITIVE LOGITS
    hered
    0.89
    aign
    0.88
    hest
    0.88
    imates
    0.86
    ours
    0.85
    uries
    0.82
    resso
    0.82
    ura
    0.80
    imen
    0.80
    sheet
    0.80
    Activations Density 0.138%

    No Known Activations