© 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. 1-RES-JB
    11. 8535
    Prev
    Next
    INDEX
    Explanations

    specific references to public transportation systems

    oai_token-act-pair · gpt-3.5-turbo

    references to public transportation systems and authorities

    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
    aunder
    -0.69
     nomine
    -0.69
    erd
    -0.68
    monds
    -0.67
    Ô
    -0.67
    amental
    -0.66
    arag
    -0.66
    Downloadha
    -0.64
     confidential
    -0.63
    ielding
    -0.63
    POSITIVE LOGITS
     Transit
    1.15
     transit
    0.83
    WA
    0.81
     Facilities
    0.78
     Patrol
    0.78
     Blazers
    0.77
     buses
    0.75
    Eye
    0.75
     Simulator
    0.75
    gress
    0.75
    Activations Density 0.009%

    No Known Activations