© 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. 7-RES-JB
    11. 5221
    Prev
    Next
    INDEX
    Explanations

    patterns and trends

    oai_token-act-pair · gpt-3.5-turbo

    patterns and concepts related to approaches, attitudes, and trends in health and social issues

    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
     favourites
    -0.65
    Parts
    -0.57
     Mouth
    -0.57
    racuse
    -0.56
     CLR
    -0.55
    ergy
    -0.54
     Legions
    -0.54
    ummies
    -0.53
     Mush
    -0.53
    parts
    -0.52
    POSITIVE LOGITS
     extends
    1.00
     coincides
    0.95
     contrasts
    0.95
     implies
    0.91
     ensures
    0.90
     applies
    0.89
     culmin
    0.89
     belongs
    0.88
     coincided
    0.88
     assumes
    0.88
    Activations Density 0.224%

    No Known Activations