© 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. 0-RES-JB
    11. 13009
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, specifically places with 'Fort' in the name

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of "Fort" related to a specific location or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     breakout
    -0.66
     due
    -0.64
     ordered
    -0.64
     Sharma
    -0.64
     root
    -0.62
     Krishna
    -0.62
     cycling
    -0.62
     fan
    -0.61
     crossover
    -0.61
     removable
    -0.60
    POSITIVE LOGITS
    Fort
    3.84
    fort
    1.80
    Thirty
    1.37
    Nin
    1.35
    fortune
    1.26
    Twenty
    1.25
    Ele
    1.23
    Fif
    1.20
    Eight
    1.15
    Four
    1.15
    Activations Density 0.013%

    No Known Activations