© 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. 21793
    Prev
    Next
    INDEX
    Explanations

    queries or prompts within parentheses

    oai_token-act-pair · gpt-3.5-turbo

    closing parentheses in sentences

    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
    arde
    -0.70
    rament
    -0.69
    ouk
    -0.69
    ãĥ¥
    -0.66
    resa
    -0.65
    zeb
    -0.65
    rocal
    -0.65
     luxury
    -0.65
    ĸļ
    -0.64
    bris
    -0.64
    POSITIVE LOGITS
    âķ
    0.78
    TPS
    0.76
    >]
    0.75
     Conversely
    0.72
    */
    0.70
    âĵĺ
    0.69
    RESULTS
    0.68
    âĹ¼
    0.68
    while
    0.66
    }.
    0.64
    Activations Density 0.196%

    No Known Activations