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. 7-RES-JB
    6. 20425
    Prev
    Next
    INDEX
    Explanations

    dates written in the format Month Day, Year

    oai_token-act-pair · gpt-3.5-turbo

    dates and their corresponding events or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.76
    vs
    -0.65
    etheless
    -0.65
    paio
    -0.62
     parap
    -0.62
     indisp
    -0.61
    accompanied
    -0.60
    keley
    -0.59
     pregn
    -0.58
     millenn
    -0.58
    POSITIVE LOGITS
     Invalid
    0.86
     [+]
    0.75
    rils
    0.68
     Tweet
    0.68
     09
    0.68
     06
    0.67
    Invalid
    0.67
     08
    0.66
     04
    0.65
     05
    0.64
    Activations Density 0.088%

    No Known Activations