Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 16278
    Prev
    Next
    INDEX
    Explanations

    dates or events denoted by "Day X"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crim
    -0.71
     fin
    -0.65
     ACL
    -0.64
     graphene
    -0.63
     rap
    -0.62
     shrink
    -0.62
     capac
    -0.61
     lob
    -0.59
     revers
    -0.59
     range
    -0.58
    POSITIVE LOGITS
    Day
    4.00
    day
    2.38
    DAY
    2.29
     Day
    2.10
    Days
    1.94
    Night
    1.79
     DAY
    1.63
    Month
    1.51
    morning
    1.50
    Hour
    1.49
    Activations Density 0.008%

    No Known Activations