© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 22691
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations, particularly those including the term "Fort"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Fort."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incentives
    -0.73
     gearing
    -0.59
    Publisher
    -0.58
     referendum
    -0.58
    nder
    -0.56
     Unlimited
    -0.56
    inators
    -0.55
    Companies
    -0.55
     Primordial
    -0.55
     downward
    -0.54
    POSITIVE LOGITS
     Lauderdale
    1.27
    uitous
    1.16
    ieth
    1.09
    itude
    1.09
     Worth
    1.01
    resses
    0.98
    ifications
    0.92
    inet
    0.90
    uit
    0.90
     Hood
    0.88
    Activations Density 0.026%

    No Known Activations