© 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. 6-RES-JB
    11. 11933
    Prev
    Next
    INDEX
    Explanations

    dates in various formats (day/month/year or month/year)

    oai_token-act-pair · gpt-3.5-turbo

    dates and times related to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gib
    -0.51
     preservation
    -0.48
     VIDEOS
    -0.45
     reference
    -0.45
     perpetual
    -0.45
     includes
    -0.44
     abbre
    -0.44
    alog
    -0.43
     dwell
    -0.43
     emphasizes
    -0.43
    POSITIVE LOGITS
    ruary
    0.61
    ember
    0.57
    ixties
    0.55
    furt
    0.54
    âĸĪâĸĪ
    0.53
    phrine
    0.52
     morning
    0.51
    eme
    0.50
    Aug
    0.50
     afternoon
    0.50
    Activations Density 0.452%

    No Known Activations