© 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. 6-RES-JB
    11. 13730
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific points or important aspects within larger discussions or contexts

    oai_token-act-pair · gpt-3.5-turbo

    colons indicating a list or separation of ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oud
    -0.78
    undai
    -0.69
     troubles
    -0.69
    ebin
    -0.66
    apan
    -0.66
    ãĤ¡
    -0.66
    leased
    -0.66
    oen
    -0.66
    ridor
    -0.65
    yan
    -0.65
    POSITIVE LOGITS
     namely
    1.14
     Provided
    0.98
     Whereas
    0.81
     Firstly
    0.77
     Scores
    0.76
     Stories
    0.76
     Journals
    0.72
     Countries
    0.70
     Cases
    0.68
     "âĢ¦
    0.68
    Activations Density 0.112%

    No Known Activations