© 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. 11-RES-JB
    11. 20461
    Prev
    Next
    INDEX
    Explanations

    security and safety-related instructions or warnings

    oai_token-act-pair · gpt-3.5-turbo

    imperative statements or advice directing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ELD
    -0.74
    atz
    -0.64
    Said
    -0.62
    ById
    -0.62
    lishes
    -0.61
    Winner
    -0.58
     crashed
    -0.55
    fred
    -0.55
    lime
    -0.55
    ammed
    -0.55
    POSITIVE LOGITS
     beware
    1.40
     consult
    1.26
     avoid
    1.16
     carefully
    1.15
     ALWAYS
    1.13
     acquaint
    1.12
     consider
    1.09
     heed
    1.08
     refrain
    1.08
    avoid
    1.08
    Activations Density 0.215%

    No Known Activations