© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 4767
    Prev
    Next
    INDEX
    Explanations

    locations or place names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    "fall" or "falling" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cess
    -0.69
    enthal
    -0.66
    gebra
    -0.65
    andi
    -0.65
    oxide
    -0.65
    din
    -0.64
    zsche
    -0.62
    dd
    -0.61
    ÃŁ
    -0.61
    atures
    -0.61
    POSITIVE LOGITS
    alion
    0.76
    auga
    0.73
    lished
    0.69
    akery
    0.67
    ificent
    0.64
    ippi
    0.63
    RAFT
    0.63
    76561
    0.61
     Beaut
    0.60
    ealous
    0.59
    Activations Density 0.260%

    No Known Activations