Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6971
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism or opposition in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to criticism and opposing viewpoints related to policies and laws

    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
    owship
    -0.77
    uras
    -0.67
    CLASSIFIED
    -0.66
    eret
    -0.65
    Redd
    -0.65
    versible
    -0.62
    HAHA
    -0.62
     Adinida
    -0.58
    unin
    -0.58
    AAAAAAAA
    -0.58
    POSITIVE LOGITS
     contend
    1.27
     allege
    1.20
     argue
    1.16
     accuse
    1.16
     say
    1.03
    ervatives
    0.99
     claim
    0.97
    paces
    0.95
     concede
    0.94
     assail
    0.94
    Activations Density 0.065%

    No Known Activations