© 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. 13850
    Prev
    Next
    INDEX
    Explanations

    phrases containing descriptions or self-descriptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "describe" and its variations in different contexts

    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
    valid
    -0.64
    fort
    -0.62
    achable
    -0.62
    isdom
    -0.61
    needed
    -0.59
    iasm
    -0.59
     scrimmage
    -0.58
    umo
    -0.58
    othal
    -0.57
    ont
    -0.57
    POSITIVE LOGITS
     how
    0.93
     himself
    0.77
     herself
    0.73
     themselves
    0.72
     embodiments
    0.70
     symptoms
    0.69
     Patterns
    0.69
    igate
    0.68
     descriptions
    0.68
     experiences
    0.68
    Activations Density 0.069%

    No Known Activations