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. 11-RES-JB
    6. 19518
    Prev
    Next
    INDEX
    Explanations

    phrases related to current events and crises in different locations

    oai_token-act-pair · gpt-3.5-turbo

    themes related to legal actions and social conflicts involving authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    assuming
    -0.76
    âĶĢâĶĢâĶĢâĶĢ
    -0.74
    ":"/
    -0.73
     Principle
    -0.70
     Encyclopedia
    -0.70
    emphasis
    -0.69
    onom
    -0.68
    _.
    -0.65
    laughs
    -0.65
    Reviewer
    -0.65
    POSITIVE LOGITS
     collided
    1.40
     clashed
    1.32
     crashed
    1.25
     vanished
    1.20
     collapsed
    1.19
     stormed
    1.18
     exploded
    1.17
     plummeted
    1.14
     surged
    1.14
     derailed
    1.14
    Activations Density 0.442%

    No Known Activations