© 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. 8-RES-JB
    11. 4222
    Prev
    Next
    INDEX
    Explanations

    words related to radioactivity and nuclear elements

    oai_token-act-pair · gpt-3.5-turbo

    plural and past tense forms of verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NOW
    -0.64
     Doodle
    -0.63
     Yard
    -0.63
     Destroyer
    -0.63
     Blues
    -0.62
     Darling
    -0.61
    glers
    -0.61
    iage
    -0.61
    Ĥª
    -0.61
     Victory
    -0.60
    POSITIVE LOGITS
    etr
    0.92
    ith
    0.83
    idential
    0.83
    emic
    0.81
    ilon
    0.80
    itary
    0.79
    hiba
    0.79
    peria
    0.79
    estial
    0.79
    ophile
    0.78
    Activations Density 0.125%

    No Known Activations