© 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. 9-RES-JB
    11. 7168
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geographical locations and specific entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ufact
    -0.59
    vertisement
    -0.56
     Blossom
    -0.56
    tumblr
    -0.56
    ģĸ
    -0.54
    dylib
    -0.54
     Pwr
    -0.54
    etooth
    -0.53
    zona
    -0.53
    ADRA
    -0.53
    POSITIVE LOGITS
    tsky
    0.62
    reshold
    0.60
    lde
    0.58
    aternity
    0.56
     Pegasus
    0.54
     Tactics
    0.54
     Torment
    0.53
    deen
    0.52
    utsche
    0.50
    asha
    0.49
    Activations Density 0.797%

    No Known Activations