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. 9-RES-JB
    6. 21632
    Prev
    Next
    INDEX
    Explanations

    phrases related to activism and standing up for rights or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    expressions of unity and collective action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stereotypical
    -0.89
    imilar
    -0.80
    Generally
    -0.80
     interacts
    -0.78
     interacted
    -0.77
    umably
    -0.77
     inappropriately
    -0.76
    mentioned
    -0.76
     attributed
    -0.76
    similar
    -0.76
    POSITIVE LOGITS
     FIGHT
    1.02
     Resistance
    0.95
     patri
    0.94
     AMERICA
    0.94
     DEM
    0.89
     Tonight
    0.87
    Enough
    0.84
     Courage
    0.82
     Fight
    0.82
     salute
    0.81
    Activations Density 0.804%

    No Known Activations