© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 6748
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures or events

    oai_token-act-pair · gpt-3.5-turbo

    the word "stonewall" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.71
    chance
    -0.71
    Downloadha
    -0.70
    purpose
    -0.69
    CONCLUS
    -0.68
     Franch
    -0.66
    REDACTED
    -0.65
    Posts
    -0.65
    VIS
    -0.64
    WAYS
    -0.62
    POSITIVE LOGITS
    onew
    1.25
    alling
    0.94
    alled
    0.91
    ©¶æ¥µ
    0.89
    eties
    0.88
    ãĤ©
    0.87
    terness
    0.86
    inx
    0.83
    ield
    0.81
    mallow
    0.80
    Activations Density 0.013%

    No Known Activations