© 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. 1791
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning locations

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or areas surrounding particular places

    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
     partName
    -0.78
     Canyon
    -0.65
    atis
    -0.63
     craw
    -0.63
    txt
    -0.63
    orers
    -0.62
    undrum
    -0.62
    Äĩ
    -0.61
     Doctrine
    -0.60
    aird
    -0.59
    POSITIVE LOGITS
     alike
    0.72
     respectively
    0.66
    senal
    0.62
    eele
    0.61
     Mood
    0.59
    soDeliveryDate
    0.58
    )=(
    0.58
    IGH
    0.57
    raviolet
    0.57
    =-=-=-=-=-=-=-=-
    0.55
    Activations Density 0.047%

    No Known Activations