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. 11-RES-JB
    6. 4396
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscription attempts and error messages

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to retrying or resubmitting actions after failure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.80
     awa
    -0.63
     oun
    -0.63
    ccording
    -0.57
    lihood
    -0.53
    everal
    -0.52
    eatures
    -0.52
     includ
    -0.52
    anwhile
    -0.51
     remem
    -0.51
    POSITIVE LOGITS
     unfocusedRange
    0.60
    Subscribe
    0.58
    Invalid
    0.57
    olesterol
    0.55
    later
    0.54
    Try
    0.54
     istg
    0.54
    ingly
    0.53
    Sorry
    0.52
    Prev
    0.52
    Activations Density 0.011%

    No Known Activations