Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-RES-JB
    6. 13183
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal beliefs or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of opinion or belief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.63
    ankind
    -0.61
     Written
    -0.60
    Ü
    -0.60
    abi
    -0.59
    begin
    -0.58
    guard
    -0.58
    mentioned
    -0.57
    lite
    -0.57
    beam
    -0.57
    POSITIVE LOGITS
    iewicz
    0.72
    olate
    0.71
    olated
    0.67
     passionately
    0.61
     himself
    0.60
    terson
    0.60
    aspers
    0.59
     Tues
    0.56
    phas
    0.56
    ajor
    0.55
    Activations Density 0.188%

    No Known Activations