© 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. 14754
    Prev
    Next
    INDEX
    Explanations

    phrases describing a physical environment with a specific focus on the presence of an object or action in the air

    oai_token-act-pair · gpt-3.5-turbo

    references to elements in the atmosphere or surrounding environment

    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
    ILA
    -0.78
    illin
    -0.68
    mercial
    -0.63
    ideon
    -0.62
    edIn
    -0.61
    ERC
    -0.60
    ailable
    -0.58
    lav
    -0.58
    antes
    -0.58
     Tumblr
    -0.57
    POSITIVE LOGITS
     hurry
    0.79
     vicinity
    0.79
     drawer
    0.77
     somewhere
    0.75
    soDeliveryDate
    0.71
     equation
    0.67
     pocket
    0.67
     area
    0.66
    FTWARE
    0.65
     anytime
    0.65
    Activations Density 0.287%

    No Known Activations