© 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. 0-RES-JB
    11. 2909
    Prev
    Next
    INDEX
    Explanations

    mentions of the city "Austin"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the city of Austin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mor
    -0.69
     chrom
    -0.68
    thal
    -0.68
    chwitz
    -0.68
     np
    -0.67
    chrom
    -0.67
    np
    -0.67
    Prin
    -0.66
     paste
    -0.65
    paste
    -0.65
    POSITIVE LOGITS
     Austin
    3.69
    Austin
    3.36
     Dallas
    1.78
     Houston
    1.74
     Arlington
    1.67
     Texas
    1.65
    Houston
    1.65
    Dallas
    1.60
     Travis
    1.60
     SX
    1.57
    Activations Density 0.015%

    No Known Activations