© 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. 7185
    Prev
    Next
    INDEX
    Explanations

    actions or events happening

    oai_token-act-pair · gpt-3.5-turbo

    actions indicating completion or crucial moments in a sequence of events

    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
    pg
    -0.79
    *****
    -0.64
    atell
    -0.63
    ère
    -0.62
     lineback
    -0.61
    Pg
    -0.59
    twitch
    -0.59
    cms
    -0.59
    inho
    -0.58
    orst
    -0.57
    POSITIVE LOGITS
    ãĤ¢ãĥ«
    0.73
    redients
    0.69
    BuyableInstoreAndOnline
    0.68
    phas
    0.67
     Pengu
    0.65
     engagements
    0.64
     oneself
    0.63
     Tours
    0.62
     tours
    0.61
    prus
    0.60
    Activations Density 0.158%

    No Known Activations