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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10270
    Prev
    Next
    INDEX
    Explanations

    mentions of taxi cabs or related terms like 'autonomous cabs' in the context of different scenarios

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cab" and related terms

    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
    \\\\\\\\\\\\\\\\
    -0.74
     Nanto
    -0.70
     Maker
    -0.67
    OGR
    -0.63
    \\\\\\\\
    -0.63
     Loch
    -0.62
     Sandy
    -0.61
     Honour
    -0.61
     wills
    -0.61
    BOOK
    -0.60
    POSITIVE LOGITS
    abs
    1.19
    itol
    0.92
    ulous
    0.88
    ensed
    0.87
    ence
    0.85
    ibilities
    0.85
    undo
    0.84
    orb
    0.83
    acus
    0.82
    lip
    0.81
    Activations Density 0.006%

    No Known Activations