© 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. 7-RES-JB
    11. 24041
    Prev
    Next
    INDEX
    Explanations

    locations or places in a news or report context

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcsstore
    -1.08
    xon
    -0.78
    olson
    -0.73
    ulty
    -0.71
    ocobo
    -0.70
     Investigations
    -0.70
    Lear
    -0.69
    zees
    -0.69
    antom
    -0.68
    ornia
    -0.67
    POSITIVE LOGITS
    scape
    0.95
     outskirts
    0.89
     Syri
    0.85
     suburbs
    0.84
     Abbas
    0.83
     Homs
    0.83
     Jerusalem
    0.81
     suburb
    0.81
     Tripoli
    0.80
     Mosul
    0.79
    Activations Density 0.140%

    No Known Activations