© 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. 7864
    Prev
    Next
    INDEX
    Explanations

    dates and times

    oai_token-act-pair · gpt-3.5-turbo

    temporal references, particularly focusing on specific days, weeks, months, and years

    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
     bearer
    -0.68
     bom
    -0.63
    é¾įå
    -0.61
    aum
    -0.60
    Hub
    -0.60
    éĹĺ
    -0.59
     univers
    -0.59
     orig
    -0.58
     Agric
    -0.57
     Izan
    -0.56
    POSITIVE LOGITS
    ixties
    0.84
    xual
    0.83
     âĶľ
    0.75
    rils
    0.71
     morning
    0.70
    hower
    0.69
    ties
    0.69
     afternoon
    0.69
     sidx
    0.69
    steen
    0.68
    Activations Density 0.096%

    No Known Activations