© 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. 306
    Prev
    Next
    INDEX
    Explanations

    phrases ending with a period, accompanied by a numerical code-like sequence

    oai_token-act-pair · gpt-3.5-turbo

    indicators of serious issues or crises

    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
    hement
    -0.79
     grouping
    -0.73
    xual
    -0.70
     footing
    -0.63
    lling
    -0.63
     undermin
    -0.63
     scrambling
    -0.61
     exha
    -0.60
     estranged
    -0.59
     tink
    -0.59
    POSITIVE LOGITS
    ³³³³
    1.16
    ³³³
    0.96
    Trivia
    0.95
    ³³³³³³³³³³³³³³³³
    0.95
    Posted
    0.95
    ³³³³³³³³
    0.95
    âĶĢâĶĢâĶĢâĶĢ
    0.93
    Quantity
    0.92
    Synopsis
    0.91
    âĸ¬âĸ¬
    0.91
    Activations Density 0.165%

    No Known Activations