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. 3-RES-JB
    6. 6733
    Prev
    Next
    INDEX
    Explanations

    statements related to social and political issues, as well as values and beliefs

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ESE
    -0.73
    culus
    -0.72
    odcast
    -0.69
    bo
    -0.69
    agle
    -0.68
    :(
    -0.68
    agen
    -0.68
    wic
    -0.65
    wire
    -0.65
    aws
    -0.65
    POSITIVE LOGITS
     hence
    1.09
     consequently
    1.07
     therefore
    1.05
     thus
    1.05
     thereby
    1.03
     possibly
    0.90
     then
    0.88
     vice
    0.80
     thence
    0.80
     consequ
    0.79
    Activations Density 0.952%

    No Known Activations