© 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. 13896
    Prev
    Next
    INDEX
    Explanations

    references to activities or events related to a specific individual creating or participating in certain actions

    oai_token-act-pair · gpt-3.5-turbo

    references to football or related sports activities

    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
    erenn
    -0.76
    ulative
    -0.65
    contained
    -0.64
    ente
    -0.62
    ventional
    -0.62
    governmental
    -0.61
    ohydrate
    -0.61
    ourning
    -0.60
    odge
    -0.60
    overty
    -0.60
    POSITIVE LOGITS
     ;)
    1.39
     :)
    1.21
     ðŁĻĤ
    1.18
     :-)
    1.13
     haha
    1.12
     ðŁĺ
    1.09
     lol
    0.95
    !).
    0.94
     badass
    0.91
     (@
    0.90
    Activations Density 1.347%

    No Known Activations