© 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. 2-RES-JB
    11. 9362
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Taco" with varying degrees of association or relevance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "taco" and its variations

    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
    manship
    -0.75
    kj
    -0.75
    theless
    -0.74
    igree
    -0.74
     Known
    -0.72
     Drawn
    -0.72
    20439
    -0.71
    YN
    -0.70
     ASC
    -0.69
     Citizens
    -0.66
    POSITIVE LOGITS
    rito
    1.02
     taco
    1.01
     tacos
    0.97
    otle
    0.96
     seasoning
    0.92
     Taco
    0.88
     eater
    0.87
    rio
    0.84
    anut
    0.82
     Mex
    0.82
    Activations Density 0.010%

    No Known Activations