© 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. 11-RES-JB
    11. 2218
    Prev
    Next
    INDEX
    Explanations

    commands or actions related to manipulating files or data in a technical environment

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to software functionality and customization options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.78
    Champ
    -0.70
    union
    -0.69
    united
    -0.67
    BuyableInstoreAndOnline
    -0.66
    905
    -0.63
    éĹ
    -0.61
    orah
    -0.61
    610
    -0.61
    omore
    -0.60
    POSITIVE LOGITS
     yourself
    1.38
     your
    1.30
     them
    1.16
     yourselves
    1.13
     any
    0.99
     arbitrary
    0.97
     anything
    0.96
     yours
    0.95
     whichever
    0.95
     these
    0.93
    Activations Density 0.311%

    No Known Activations