© 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. 7-RES-JB
    11. 21429
    Prev
    Next
    INDEX
    Explanations

    items or concepts that are harmful or potentially dangerous

    oai_token-act-pair · gpt-3.5-turbo

    specific items or concepts that could be categorized as unusual or diverse, often in contexts related to health, technology, or unique cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ö¼
    -0.84
     Approach
    -0.72
    vous
    -0.65
    ablishment
    -0.65
    allery
    -0.63
     issuer
    -0.62
    swer
    -0.61
    ructure
    -0.60
     âĶľ
    -0.59
     Fiscal
    -0.59
    POSITIVE LOGITS
    coins
    0.84
    prints
    0.82
     buffs
    0.76
    notes
    0.72
    isively
    0.72
     clones
    0.70
     copies
    0.70
     loads
    0.69
    loads
    0.69
    like
    0.69
    Activations Density 0.549%

    No Known Activations