© 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. 3-RES-JB
    11. 5413
    Prev
    Next
    INDEX
    Explanations

    phrases or words containing "fort"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "fort" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.80
    MIT
    -0.71
    Magikarp
    -0.68
    interstitial
    -0.68
    Else
    -0.67
    Topics
    -0.67
    externalActionCode
    -0.64
     Koen
    -0.62
    biology
    -0.61
    PER
    -0.60
    POSITIVE LOGITS
    uitous
    1.16
    dinand
    1.09
    fort
    1.08
    ieth
    1.06
    resses
    0.96
    iors
    0.95
    ertodd
    0.93
    oise
    0.92
    ress
    0.92
    uration
    0.92
    Activations Density 0.011%

    No Known Activations