© 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. 0-RES-JB
    11. 418
    Prev
    Next
    INDEX
    Explanations

    words related to criticism and negative evaluation

    oai_token-act-pair · gpt-3.5-turbo

    instances of criticism or disparagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inct
    -0.69
     Leeds
    -0.67
     sequence
    -0.63
     pulses
    -0.62
     Cad
    -0.61
     Delivery
    -0.61
     sew
    -0.61
     Bond
    -0.61
     Grant
    -0.61
     supply
    -0.60
    POSITIVE LOGITS
     criticized
    3.30
     criticised
    2.62
     criticize
    2.24
     criticizing
    1.91
     praised
    1.90
     denounced
    1.89
     ridiculed
    1.84
     applauded
    1.81
     condemned
    1.72
     blamed
    1.60
    Activations Density 0.022%

    No Known Activations