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

    Neuronpedia

    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. 3171
    Prev
    Next
    INDEX
    Explanations

    the concept of availability or capacity for improvement

    oai_token-act-pair · gpt-3.5-turbo
    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
     choir
    -0.60
    ilet
    -0.59
     Sophia
    -0.58
    aca
    -0.58
    obook
    -0.58
     Pastebin
    -0.57
     Esk
    -0.57
     Nieto
    -0.57
     Outbreak
    -0.54
    ynchron
    -0.53
    POSITIVE LOGITS
     for
    0.93
    for
    0.74
    eous
    0.73
     left
    0.69
     enough
    0.69
    OIL
    0.67
    atility
    0.66
     allotted
    0.65
     space
    0.65
    atile
    0.65
    Activations Density 0.074%

    No Known Activations