© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 20199
    Prev
    Next
    INDEX
    Explanations

    words related to criticism and strong negative reactions towards specific individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    negative statements or criticisms directed towards individuals or groups

    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
    archment
    -0.68
     ILCS
    -0.67
    hazard
    -0.66
    ance
    -0.66
    iac
    -0.65
    OTE
    -0.65
    1920
    -0.64
    hyde
    -0.63
    ason
    -0.63
    thing
    -0.63
    POSITIVE LOGITS
     criticism
    0.94
     criticisms
    0.89
     suggestions
    0.87
     critics
    0.86
     comments
    0.80
     questioning
    0.78
     commenters
    0.77
     critic
    0.77
     remarks
    0.76
     accusations
    0.73
    Activations Density 0.213%

    No Known Activations