© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 9668
    Prev
    Next
    INDEX
    Explanations

    mentions of the city of Dallas and related entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Dallas

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

    No Comments

    Negative Logits
    udding
    -0.72
    oys
    -0.72
     captcha
    -0.66
    âĵĺ
    -0.65
    elvet
    -0.65
    iltration
    -0.65
    fty
    -0.64
    udic
    -0.64
    icably
    -0.63
     Britann
    -0.63
    POSITIVE LOGITS
     Mavericks
    1.12
     Cowboys
    0.92
    Stars
    0.92
    hyde
    0.88
    Dallas
    0.87
     Dallas
    0.85
    illo
    0.80
    burg
    0.78
     Baptist
    0.77
     Stars
    0.77
    Activations Density 0.012%

    No Known Activations