Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 3311
    Prev
    Next
    INDEX
    Explanations

    references to public transportation vehicles, particularly buses

    oai_token-act-pair · gpt-3.5-turbo

    references to public transportation, specifically buses and WiFi connectivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uity
    -0.91
    uments
    -0.87
    uous
    -0.73
    eties
    -0.72
    atorial
    -0.72
    ificent
    -0.70
    ured
    -0.69
    rament
    -0.69
    ocratic
    -0.68
    orius
    -0.68
    POSITIVE LOGITS
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.92
     Dracula
    0.80
    isSpecialOrderable
    0.75
    enance
    0.75
    dylib
    0.73
     Giul
    0.67
    adesh
    0.66
    udeb
    0.65
     Penguin
    0.65
    accompanied
    0.64
    Activations Density 0.042%

    No Known Activations