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. 8806
    Prev
    Next
    INDEX
    Explanations

    phrases related to failure or shortcomings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "failed to."

    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
    soDeliveryDate
    -0.84
    Reader
    -0.74
    mails
    -0.70
    Flo
    -0.69
     Printed
    -0.68
    rolled
    -0.66
    orno
    -0.66
    going
    -0.65
    umes
    -0.65
    calling
    -0.64
    POSITIVE LOGITS
     comply
    1.39
     adequately
    1.23
     qualify
    1.23
     heed
    1.22
     recognize
    1.22
     resolve
    1.22
     satisfy
    1.21
     adhere
    1.20
     fulfill
    1.19
     anticipate
    1.17
    Activations Density 0.067%

    No Known Activations