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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 24429
    Prev
    Next
    INDEX
    Explanations

    technical terms related to specifications or measurements

    oai_token-act-pair · gpt-3.5-turbo

    statistical terminology and concepts

    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
    ersen
    -0.86
    natureconservancy
    -0.68
    entin
    -0.61
    lihood
    -0.61
    jriwal
    -0.60
    ability
    -0.60
    xit
    -0.59
    yrus
    -0.58
    ulic
    -0.57
    enment
    -0.57
    POSITIVE LOGITS
     unpop
    0.73
     dilig
    0.64
    ¼
    0.62
     metic
    0.59
     unden
    0.55
     advoc
    0.54
    âĸ¬
    0.53
     accomp
    0.53
    Į
    0.52
    userc
    0.52
    Activations Density 0.427%

    No Known Activations