© 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. 10-RES-JB
    11. 6001
    Prev
    Next
    INDEX
    Explanations

    reasons or justifications

    oai_token-act-pair · gpt-3.5-turbo

    statements that explain various reasons for actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.73
    Appearance
    -0.68
    ortunately
    -0.66
    ccording
    -0.66
    hazard
    -0.65
    agog
    -0.65
    chio
    -0.64
    chance
    -0.63
    zeb
    -0.63
    ãĥĪ
    -0.62
    POSITIVE LOGITS
     why
    1.68
    why
    1.30
    abl
    1.18
     WHY
    1.18
     behind
    1.08
     Why
    0.98
     cited
    0.93
    Why
    0.89
     rationale
    0.76
     justifying
    0.73
    Activations Density 0.035%

    No Known Activations