© 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. 8-RES-JB
    11. 17693
    Prev
    Next
    INDEX
    Explanations

    references to specific requests or prohibitions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific food items and other tangible concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortment
    -0.76
     Bowen
    -0.67
    ometimes
    -0.65
    hap
    -0.62
     Ezek
    -0.60
    ahime
    -0.59
    eals
    -0.58
    Fig
    -0.58
     HIGH
    -0.57
    ffield
    -0.56
    POSITIVE LOGITS
     whatsoever
    1.60
     nor
    1.46
     anymore
    1.28
     slightest
    1.05
    nor
    0.85
     anywhere
    0.85
     requirement
    0.82
     except
    0.82
     avail
    0.82
     markings
    0.76
    Activations Density 0.411%

    No Known Activations