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. 3-RES-JB
    6. 21462
    Prev
    Next
    INDEX
    Explanations

    headlines or titles of news articles

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "headline"

    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
    ioch
    -0.79
    ometers
    -0.77
    aum
    -0.73
    ajor
    -0.73
    asca
    -0.72
    wagen
    -0.71
    cius
    -0.67
    uv
    -0.67
    olin
    -0.67
    icum
    -0.66
    POSITIVE LOGITS
     headline
    1.10
     headlined
    0.96
     headlines
    0.95
    ãĥŀ
    0.84
    bug
    0.82
    LINE
    0.81
    lined
    0.77
    AGE
    0.77
    NAME
    0.76
    Barn
    0.75
    Activations Density 0.008%

    No Known Activations