© 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. 11-RES-JB
    11. 21250
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism or opposition

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words that express criticism and concern regarding fairness and justice

    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
    iets
    -0.86
    lain
    -0.76
    lined
    -0.76
    ership
    -0.75
    icip
    -0.74
    rients
    -0.74
    ESE
    -0.73
    bilt
    -0.72
    nergy
    -0.72
    glomer
    -0.70
    POSITIVE LOGITS
     counterproductive
    1.52
     unethical
    1.43
     immoral
    1.42
     unconstitutional
    1.42
     irresponsible
    1.37
     discriminatory
    1.36
     degrading
    1.34
     ineffective
    1.32
     harmful
    1.31
     unjust
    1.30
    Activations Density 0.129%

    No Known Activations