© 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. 4-RES-JB
    11. 20854
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Tribeca."

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "tribe" and its variations

    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
     sink
    -0.69
     lid
    -0.65
     streng
    -0.64
     redirect
    -0.63
     Cascade
    -0.61
     toxins
    -0.61
     funnel
    -0.61
     fundamentals
    -0.60
    ACP
    -0.60
     Dresden
    -0.59
    POSITIVE LOGITS
    ril
    0.98
    union
    0.94
    eln
    0.92
    orough
    0.91
    ally
    0.89
    als
    0.88
    emate
    0.88
    uli
    0.88
    adic
    0.87
    rog
    0.86
    Activations Density 0.014%

    No Known Activations