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. 8-RES-JB
    6. 5688
    Prev
    Next
    INDEX
    Explanations

    phrases related to accomplishments or recognition

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agin
    -0.81
     mosqu
    -0.78
     dime
    -0.71
     contracted
    -0.70
     democrat
    -0.68
     challeng
    -0.67
     commonplace
    -0.65
     trade
    -0.65
     transact
    -0.65
    esse
    -0.65
    POSITIVE LOGITS
     However
    1.23
     Afterwards
    1.20
     Initially
    1.16
     Firstly
    1.09
     Upon
    1.04
     Though
    1.02
     Originally
    1.00
     Unfortunately
    1.00
     Whilst
    1.00
     According
    0.99
    Activations Density 0.513%

    No Known Activations