© 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. 11462
    Prev
    Next
    INDEX
    Explanations

    references to specific institutions, like universities and political entities, with a focus on acronyms or abbreviated names

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "CM" followed by numerical values

    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
     sidx
    -0.82
    lihood
    -0.82
    raltar
    -0.80
    rets
    -0.78
    ãĥ¼ãĥĨ
    -0.77
    via
    -0.75
    spell
    -0.73
    ãĤ¯
    -0.72
     Machina
    -0.72
    furt
    -0.71
    POSITIVE LOGITS
    ODE
    0.87
    trop
    0.78
    illon
    0.77
    OS
    0.75
     Punk
    0.75
    apper
    0.74
    ancel
    0.74
    CP
    0.74
    OUNT
    0.74
    ategory
    0.74
    Activations Density 0.006%

    No Known Activations