© 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. 10-RES-JB
    11. 8572
    Prev
    Next
    INDEX
    Explanations

    phrases related to prohibitions or warnings

    oai_token-act-pair · gpt-3.5-turbo

    clauses that introduce conditions or stipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.62
     Voting
    -0.62
    Luck
    -0.60
    aciously
    -0.58
     Equity
    -0.56
     Admission
    -0.56
    desktop
    -0.55
    Eye
    -0.54
    riger
    -0.54
     roaring
    -0.54
    POSITIVE LOGITS
     involves
    1.33
     violates
    1.29
     contains
    1.27
     exceeds
    1.26
     requires
    1.21
     satisfies
    1.19
     incorporates
    1.19
     contradicts
    1.19
     lacks
    1.18
     occurs
    1.18
    Activations Density 0.138%

    No Known Activations