© 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. 2-RES-JB
    11. 21789
    Prev
    Next
    INDEX
    Explanations

    locations or place names

    oai_token-act-pair · gpt-3.5-turbo

    the term "Mont" and its variations, indicating a focus on geographical references or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cial
    -0.73
    Wan
    -0.66
     abund
    -0.65
     UID
    -0.64
    OTS
    -0.63
    glers
    -0.63
    ãģĦ
    -0.62
    volume
    -0.60
     abusive
    -0.60
    ãĥĩ
    -0.59
    POSITIVE LOGITS
    gomery
    1.30
    mont
    1.20
    fort
    1.05
    agne
    0.98
    erey
    0.96
    eneg
    0.94
    aine
    0.79
    ois
    0.78
    aste
    0.77
    aire
    0.76
    Activations Density 0.007%

    No Known Activations