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. 8-RES-JB
    6. 18319
    Prev
    Next
    INDEX
    Explanations

    hashtags and trending topics on social media

    oai_token-act-pair · gpt-3.5-turbo

    references to hashtags and social media trends, particularly those related to Martin Luther King Jr

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ity
    -0.91
    igan
    -0.83
    fitting
    -0.81
    ade
    -0.78
    iations
    -0.78
    iness
    -0.77
    ades
    -0.76
    lust
    -0.76
    isbury
    -0.76
    wind
    -0.75
    POSITIVE LOGITS
    userc
    0.69
    İĭ
    0.68
    @@@@@@@@
    0.68
    ð
    0.68
    Ĩ
    0.67
    ãħĭ
    0.66
    @@@@
    0.66
     Rodham
    0.66
    vernment
    0.66
    à¼
    0.65
    Activations Density 0.116%

    No Known Activations