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. 1-RES-JB
    6. 4158
    Prev
    Next
    INDEX
    Explanations

    statements or declarations made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stated."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vernment
    -0.68
    brance
    -0.67
    iling
    -0.66
    apps
    -0.65
    alos
    -0.64
    abies
    -0.64
     sacked
    -0.64
    illard
    -0.64
     Cats
    -0.64
    marine
    -0.62
    POSITIVE LOGITS
    gow
    0.95
     stated
    0.94
     mentions
    0.76
     stating
    0.76
     bluntly
    0.75
    WER
    0.72
    :]
    0.72
    TextColor
    0.72
     indicates
    0.71
    :"
    0.71
    Activations Density 0.022%

    No Known Activations