© 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. 10-RES-JB
    11. 2878
    Prev
    Next
    INDEX
    Explanations

    the word "Ind" or "Ind" followed by a number indicating a specific indicator

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Ind" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deaf
    -0.70
     compr
    -0.69
     litter
    -0.68
     behav
    -0.67
     cascade
    -0.64
    sonian
    -0.64
     Pastebin
    -0.63
     halfway
    -0.62
    âĨij
    -0.60
     closest
    -0.60
    POSITIVE LOGITS
    ividually
    1.56
    irect
    1.54
    epend
    1.42
    icative
    1.41
    icator
    1.39
    ebted
    1.37
    oor
    1.32
    icators
    1.32
    igenous
    1.30
    emn
    1.29
    Activations Density 0.022%

    No Known Activations