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. 16431
    Prev
    Next
    INDEX
    Explanations

    legal and political issues being discussed or debated

    oai_token-act-pair · gpt-3.5-turbo

    discussions centered around various social and political issues

    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
    ramid
    -0.80
    urses
    -0.80
    ellow
    -0.78
    son
    -0.75
    ãĥ³ãĤ¸
    -0.75
    ramids
    -0.72
    glas
    -0.72
    sis
    -0.72
    emouth
    -0.72
    bones
    -0.71
    POSITIVE LOGITS
     plag
    0.99
     confronting
    0.96
     arising
    0.90
     raised
    0.89
     flared
    0.88
     affecting
    0.87
     facing
    0.86
     relating
    0.85
     resolved
    0.83
     unresolved
    0.83
    Activations Density 0.064%

    No Known Activations