© 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. 9-RES-JB
    11. 9853
    Prev
    Next
    INDEX
    Explanations

    connections or relationships between different elements or factors

    oai_token-act-pair · gpt-3.5-turbo

    terms that suggest evidence, implications, or indicators of a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quer
    -0.76
    ighth
    -0.75
    enium
    -0.74
    76561
    -0.74
    @#&
    -0.72
    arak
    -0.70
    agues
    -0.70
    apest
    -0.69
    ild
    -0.69
    ulu
    -0.69
    POSITIVE LOGITS
     displeasure
    0.91
     otherwise
    0.84
     impending
    0.84
     disobedience
    0.82
     willingness
    0.77
     urgency
    0.77
    ively
    0.76
     imminent
    0.76
     intent
    0.75
     superiority
    0.74
    Activations Density 0.090%

    No Known Activations