© 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. 12405
    Prev
    Next
    INDEX
    Explanations

    short phrases describing actions or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to change and transitions in society or personal contexts

    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
     armour
    -0.79
     tear
    -0.78
     taps
    -0.76
     colour
    -0.76
     hyd
    -0.76
     armoured
    -0.75
     invent
    -0.73
     tanks
    -0.73
     mustard
    -0.72
     displaced
    -0.72
    POSITIVE LOGITS
    Enlarge
    1.08
     Ratio
    0.99
    Marginal
    0.92
     Debate
    0.90
     Levels
    0.90
     Conclusion
    0.90
    Definition
    0.89
    Merit
    0.89
     Disorder
    0.89
    Premium
    0.89
    Activations Density 0.195%

    No Known Activations