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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 19619
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms related to media or entertainment

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people or entities, particularly those related to media or documents

    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
    arial
    -0.98
    inates
    -0.90
    rador
    -0.79
    antine
    -0.77
    uate
    -0.76
    egal
    -0.75
    inate
    -0.74
    onis
    -0.74
    ranean
    -0.74
    essor
    -0.73
    POSITIVE LOGITS
    nesday
    1.18
    ÅĤ
    0.78
    tip
    0.78
    shirt
    0.77
     Whe
    0.76
    atts
    0.75
    DIV
    0.75
    Cry
    0.75
    ashington
    0.73
    Commerce
    0.73
    Activations Density 0.038%

    No Known Activations