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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6972
    Prev
    Next
    INDEX
    Explanations

    locations/cities where criminal events occurred

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific locations and cities

    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
    Not in Any Lists

    No Comments

    Negative Logits
    inyl
    -0.66
    nav
    -0.62
     digit
    -0.60
     extant
    -0.58
    ãĤ¨
    -0.58
    letter
    -0.57
    cur
    -0.57
    angible
    -0.57
    emonic
    -0.56
    ãĤ¦
    -0.56
    POSITIVE LOGITS
     suburb
    1.19
     airspace
    1.07
     suburbs
    1.06
     yesterday
    1.00
     injuring
    0.93
     Heights
    0.92
     Township
    0.91
     neighborhoods
    0.90
     countryside
    0.90
     neighbourhoods
    0.89
    Activations Density 0.206%

    No Known Activations