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. 12-RES-JB
    6. 6959
    Prev
    Next
    INDEX
    Explanations

    instances of conflict, protest, and controversy within social and political contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    concepts related to conflict and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Inquisition
    -0.47
    ocating
    -0.47
    ITNESS
    -0.45
    Privacy
    -0.45
    tions
    -0.43
    nosis
    -0.42
    ndra
    -0.42
    estyles
    -0.42
    ativity
    -0.41
    LESS
    -0.41
    POSITIVE LOGITS
     from
    1.25
    from
    1.20
     FROM
    1.00
     From
    0.96
    From
    0.85
     awa
    0.65
     fro
    0.58
     thence
    0.58
     away
    0.56
     out
    0.55
    Activations Density 1.045%

    No Known Activations