© 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. 10-RES-JB
    11. 11438
    Prev
    Next
    INDEX
    Explanations

    city names

    oai_token-act-pair · gpt-3.5-turbo

    references to San Francisco and its nearby regions or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Fr
    #2 activation: 44.21
    •ans
    #3 activation: 14.23

    No Comments

    Negative Logits
    Hack
    -0.71
     Psy
    -0.63
    sworth
    -0.62
    holding
    -0.62
     Hodg
    -0.62
     Ballistic
    -0.61
     Starr
    -0.60
     Beet
    -0.58
     McInt
    -0.58
     Bard
    -0.57
    POSITIVE LOGITS
    aquin
    0.93
    Franc
    0.84
     Earthqu
    0.82
     Janeiro
    0.81
    士
    0.81
    isco
    0.80
    ña
    0.76
    San
    0.74
    itary
    0.73
    Santa
    0.71
    Activations Density 0.066%

    No Known Activations