© 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. 8-RES-JB
    11. 7764
    Prev
    Next
    INDEX
    Explanations

    mentions of sources or media outlets

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rall
    -0.74
     calendar
    -0.70
     purse
    -0.67
     tide
    -0.66
     sunset
    -0.65
     farewell
    -0.63
     goodbye
    -0.63
     homage
    -0.63
     retina
    -0.63
     gasp
    -0.62
    POSITIVE LOGITS
    com
    0.92
    net
    0.91
    org
    0.86
    cn
    0.83
     However
    0.81
    nl
    0.81
     Interestingly
    0.78
    icist
    0.78
    tv
    0.77
    acus
    0.76
    Activations Density 0.163%

    No Known Activations