© 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. 7-RES-JB
    11. 2016
    Prev
    Next
    INDEX
    Explanations

    sentences that emphasize the importance of specific information or details

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the importance of noting specific information

    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
    aired
    -0.72
     Instr
    -0.67
    idal
    -0.67
    thro
    -0.63
    QL
    -0.63
     Craw
    -0.61
    iew
    -0.61
     throats
    -0.61
    body
    -0.60
    yahoo
    -0.59
    POSITIVE LOGITS
     lest
    0.84
    ³³³
    0.78
     caveats
    0.76
     WHY
    0.74
     how
    0.70
     NOTICE
    0.70
     beforehand
    0.66
    :
    0.65
     WHEN
    0.65
     amidst
    0.65
    Activations Density 0.099%

    No Known Activations