© 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. 17098
    Prev
    Next
    INDEX
    Explanations

    specific references

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "that" in various contexts

    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
    Bow
    -0.70
    roots
    -0.70
    ahime
    -0.69
     unbeat
    -0.63
    ager
    -0.62
    åĤ
    -0.61
    uttering
    -0.60
     Unleashed
    -0.60
    roth
    -0.58
    paren
    -0.58
    POSITIVE LOGITS
    soever
    1.00
     mattered
    0.94
     participated
    0.92
     comprise
    0.85
     perished
    0.81
     participates
    0.81
     survived
    0.81
     qualifies
    0.80
    ever
    0.80
     preceded
    0.79
    Activations Density 0.164%

    No Known Activations