© 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. 7611
    Prev
    Next
    INDEX
    Explanations

    suggestions or requests for action

    oai_token-act-pair · gpt-3.5-turbo

    calls to action or requests for engagement

    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
    ELD
    -0.71
    ãĤ´
    -0.69
    codes
    -0.63
    lot
    -0.63
    GGGGGGGG
    -0.61
     looms
    -0.61
    quickShipAvailable
    -0.61
     triggered
    -0.59
     Extras
    -0.58
    ãĤ¦ãĤ¹
    -0.58
    POSITIVE LOGITS
     beware
    1.45
     refrain
    1.34
     heed
    1.25
     unite
    1.20
     consider
    1.12
     reconsider
    1.11
     rejoice
    1.11
     listen
    1.09
     buckle
    1.09
     realize
    1.07
    Activations Density 0.230%

    No Known Activations