© 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. 6-RES-JB
    11. 19763
    Prev
    Next
    INDEX
    Explanations

    terms related to the abbreviation "Ind", which can indicate a variety of contexts such as "Indonesia" or "independence"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Ind" related to different contexts or concepts

    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
    sonian
    -0.93
    EStream
    -0.88
     litter
    -0.76
     compr
    -0.74
    TION
    -0.73
    avorite
    -0.71
    collection
    -0.67
    bilt
    -0.66
    ãģį
    -0.66
    Ĥİ
    -0.65
    POSITIVE LOGITS
    ividually
    1.36
    irect
    1.33
    icative
    1.25
    ebted
    1.23
    icator
    1.18
    ifferent
    1.14
    icators
    1.10
    epend
    1.09
    ications
    1.09
    enture
    1.08
    Activations Density 0.017%

    No Known Activations