© 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. 8-RES-JB
    11. 8269
    Prev
    Next
    INDEX
    Explanations

    mentions of specific vehicle types in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    specific locations and objects involved in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exiled
    -0.78
    pora
    -0.72
     graft
    -0.69
     legions
    -0.69
     pioneers
    -0.68
     antigen
    -0.67
     PNG
    -0.66
    llan
    -0.66
     sailed
    -0.66
     giants
    -0.65
    POSITIVE LOGITS
     doorway
    0.94
     bedroom
    0.87
     bushes
    0.86
     driveway
    0.83
     vehicle
    0.83
    door
    0.80
     parked
    0.79
     porch
    0.79
     nearby
    0.78
     suspic
    0.77
    Activations Density 0.336%

    No Known Activations