© 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. 0-RES-JB
    11. 13927
    Prev
    Next
    INDEX
    Explanations

    notifications, such as those from Twitter

    oai_token-act-pair · gpt-3.5-turbo

    terms related to digital notifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vier
    -0.69
    UGC
    -0.69
    ayer
    -0.69
    perm
    -0.66
     relent
    -0.59
    iph
    -0.59
     cyn
    -0.58
    icide
    -0.57
    amide
    -0.56
     Booth
    -0.56
    POSITIVE LOGITS
    lations
    0.73
    quez
    0.70
    paio
    0.69
    quished
    0.69
    uci
    0.65
    earchers
    0.65
    FTWARE
    0.64
    undown
    0.64
    veland
    0.64
    inition
    0.62
    Activations Density 0.000%

    No Known Activations