© 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. 9-RES-JB
    11. 4614
    Prev
    Next
    INDEX
    Explanations

    time-related expressions or terms, especially related to specific weeks or weekdays

    oai_token-act-pair · gpt-3.5-turbo

    references to recent publications or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pron
    -0.67
     PAT
    -0.67
     sacrific
    -0.63
     sew
    -0.62
    icent
    -0.60
     parap
    -0.59
     ect
    -0.59
    coat
    -0.56
     ancest
    -0.56
     quo
    -0.56
    POSITIVE LOGITS
     titled
    0.83
     outlining
    0.78
     headlined
    0.76
    doi
    0.76
    NPR
    0.73
    enthal
    0.73
    published
    0.72
     detailing
    0.72
     afternoon
    0.71
    arie
    0.69
    Activations Density 0.168%

    No Known Activations