© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3506
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to geographic locations or institutions

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with geographical locations and demographics

    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
     Democr
    -0.63
     sovere
    -0.58
     multim
    -0.56
    spons
    -0.56
    gress
    -0.56
     Advertisement
    -0.56
    jriwal
    -0.56
    rawdownloadcloneembedreportprint
    -0.55
    rices
    -0.55
     Expend
    -0.54
    POSITIVE LOGITS
    eh
    0.76
    alos
    0.75
    inho
    0.73
    emouth
    0.70
    ukong
    0.70
    furt
    0.68
    mere
    0.67
    aeus
    0.66
    nah
    0.66
    erella
    0.66
    Activations Density 0.265%

    No Known Activations