© 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 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. 7-RES-JB
    11. 1682
    Prev
    Next
    INDEX
    Explanations

    phrases related to self-reflection and challenges

    oai_token-act-pair · gpt-3.5-turbo

    numerical or quantitative data relevant to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purse
    -0.74
     domestically
    -0.73
     rumored
    -0.72
     tyrann
    -0.71
     sculpt
    -0.71
     telesc
    -0.71
     reun
    -0.69
     vict
    -0.69
     territory
    -0.69
     graveyard
    -0.68
    POSITIVE LOGITS
    However
    1.58
    Instead
    1.50
    Asked
    1.45
    But
    1.45
    While
    1.44
    Although
    1.43
    Besides
    1.43
    SPONSORED
    1.42
    Refer
    1.41
    According
    1.41
    Activations Density 0.412%

    No Known Activations