© 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 EvalsExportsinterp-engineNEWAPI 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. 2-RES-JB
    11. 2487
    Prev
    Next
    INDEX
    Explanations

    mentions of the city of Dundee

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific locations and medical conditions, particularly focusing on "Dund" and references to unborn attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įå¥ij士
    -0.81
     Lans
    -0.76
     Grip
    -0.70
     Jacket
    -0.69
    è£ħ
    -0.66
     Lennon
    -0.65
     Rabbit
    -0.65
    =-=-=-=-=-=-=-=-
    -0.64
     aside
    -0.63
    UNCH
    -0.63
    POSITIVE LOGITS
    ees
    1.12
    ations
    1.02
    ee
    1.01
    ors
    1.00
    ions
    0.95
    or
    0.91
    brid
    0.90
    rum
    0.90
    estate
    0.90
    bors
    0.89
    Activations Density 0.025%

    No Known Activations