© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9862
    Prev
    Next
    INDEX
    Explanations

    references to specific dates, times, events, and announcements

    oai_token-act-pair · gpt-3.5-turbo

    scheduled events and announcements

    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
    istered
    -0.58
    ĨĴ
    -0.56
    iuses
    -0.55
     whiff
    -0.54
     insin
    -0.53
    emic
    -0.53
     existed
    -0.52
    upid
    -0.52
    aminer
    -0.51
    ecd
    -0.51
    POSITIVE LOGITS
     tomorrow
    1.09
     2019
    0.93
     someday
    0.90
    morrow
    0.85
     soon
    0.75
     hereafter
    0.75
     next
    0.74
     2021
    0.72
     anytime
    0.72
     2020
    0.69
    Activations Density 1.471%

    No Known Activations