© 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. 11-RES-JB
    11. 2836
    Prev
    Next
    INDEX
    Explanations

    words related to streets or roads

    oai_token-act-pair · gpt-3.5-turbo

    references to various locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iaries
    -0.75
    iary
    -0.66
    raint
    -0.59
    rador
    -0.59
    icable
    -0.59
    elled
    -0.58
    VERTISEMENT
    -0.58
     evidenced
    -0.57
    ����
    -0.57
    esses
    -0.56
    POSITIVE LOGITS
    ttes
    1.48
    phant
    1.20
    isure
    1.20
    agues
    1.09
    wic
    1.05
    hart
    0.98
    ws
    0.97
    utenant
    0.93
    conom
    0.93
    lla
    0.93
    Activations Density 0.075%

    No Known Activations