© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16038
    Prev
    Next
    INDEX
    Explanations

    specific references to various entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of blank space or paragraph breaks in the text

    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
    opens
    -0.92
    ooks
    -0.92
    icates
    -0.89
    aneers
    -0.87
    ambers
    -0.85
    points
    -0.85
    icts
    -0.85
    ares
    -0.85
    casts
    -0.85
    aughs
    -0.84
    POSITIVE LOGITS
     precedent
    0.78
     parity
    0.75
     outcry
    0.75
     tide
    0.74
     polarization
    0.72
     resultant
    0.72
     determination
    0.71
     persistence
    0.70
     precedence
    0.70
     aging
    0.70
    Activations Density 0.112%

    No Known Activations