© 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. 11-RES-JB
    11. 12951
    Prev
    Next
    INDEX
    Explanations

    phrases related to examining or describing different topics or aspects

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to analysis and examination of topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     externalToEVAOnly
    -0.79
    goo
    -0.72
    borgh
    -0.71
    icum
    -0.71
    caster
    -0.69
    ONSORED
    -0.68
    iere
    -0.67
    aith
    -0.67
    urat
    -0.66
    tumblr
    -0.66
    POSITIVE LOGITS
     why
    1.22
     how
    1.19
     some
    1.13
     what
    1.03
    why
    0.92
     WHY
    0.89
     whether
    0.88
     briefly
    0.88
     three
    0.84
     excerpts
    0.84
    Activations Density 0.231%

    No Known Activations