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. 10-RES-JB
    6. 4290
    Prev
    Next
    INDEX
    Explanations

    years, dates, and specific numbers

    oai_token-act-pair · gpt-3.5-turbo

    dates of founding or establishment of organizations and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hypocr
    -0.68
     pse
    -0.66
     gib
    -0.62
     behav
    -0.60
    hide
    -0.58
    ariat
    -0.57
    icate
    -0.56
    ldon
    -0.55
     snipp
    -0.55
    ggles
    -0.55
    POSITIVE LOGITS
     amidst
    0.76
     alongside
    0.74
     by
    0.74
     as
    0.68
     with
    0.68
     onwards
    0.67
     BCE
    0.67
     pursuant
    0.66
     under
    0.65
     amid
    0.65
    Activations Density 0.141%

    No Known Activations