© 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. 1-RES-JB
    11. 10415
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations or proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and their host cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rd
    -0.80
    Reviewer
    -0.70
     [+
    -0.69
     Situation
    -0.65
    NRS
    -0.63
    requ
    -0.62
    ofi
    -0.62
    football
    -0.61
    ERAL
    -0.60
    ools
    -0.58
    POSITIVE LOGITS
    auga
    1.64
     Mississ
    1.37
    gow
    0.89
    forth
    0.77
     Osh
    0.75
    atoon
    0.75
    lehem
    0.70
     Bram
    0.70
    adish
    0.69
    aret
    0.69
    Activations Density 0.021%

    No Known Activations