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. 2-RES-JB
    6. 4767
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns related to attributes or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    descriptive phrases related to lifestyle and social behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RESULTS
    -0.47
    versely
    -0.47
    CHAT
    -0.41
     McDonnell
    -0.40
     yourselves
    -0.39
    DATA
    -0.39
     Fiscal
    -0.39
    yss
    -0.38
     tentative
    -0.38
     QUEST
    -0.37
    POSITIVE LOGITS
    smanship
    0.69
    eers
    0.61
    ebted
    0.51
    Initialized
    0.50
    ploma
    0.49
    eering
    0.49
    edly
    0.47
    igraph
    0.47
     affair
    0.47
    ãĤ´ãĥ³
    0.46
    Activations Density 3.752%

    No Known Activations