© 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. 0-RES-JB
    11. 15369
    Prev
    Next
    INDEX
    Explanations

    names of locations with "Central" in them

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Central" in various contexts

    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
     lett
    -0.72
    Bey
    -0.72
    VW
    -0.69
    fig
    -0.67
    reason
    -0.66
    ãĤ¤ãĥĪ
    -0.66
    È
    -0.65
    fo
    -0.65
     Shepard
    -0.65
     bec
    -0.64
    POSITIVE LOGITS
     Central
    3.74
    Central
    2.94
    central
    2.06
     central
    1.83
     Eastern
    1.61
    Eastern
    1.40
     Southeast
    1.40
     CENT
    1.31
     Southern
    1.29
     centrally
    1.27
    Activations Density 0.011%

    No Known Activations