© 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 EvalsExportsinterp-engineNEWAPI 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. 11219
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating degree or level, such as "more important", "more impactful", and "more nuanced"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the comparison or increase of significance in various contexts

    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
    IPS
    -0.69
    leys
    -0.67
    essage
    -0.66
    xtap
    -0.63
    heid
    -0.59
    eto
    -0.59
     wee
    -0.58
    ESE
    -0.57
    ocobo
    -0.57
    alsh
    -0.56
    POSITIVE LOGITS
     than
    1.60
    than
    1.31
     Than
    1.04
     akin
    1.02
     suited
    0.94
     importantly
    0.92
     likely
    0.90
    ened
    0.88
     complicated
    0.86
     forgiving
    0.86
    Activations Density 0.100%

    No Known Activations