© 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. 19323
    Prev
    Next
    INDEX
    Explanations

    words related to criticism and disagreement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating criticism and backlash

    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
     hereby
    -0.81
    oire
    -0.76
    Words
    -0.75
    iris
    -0.73
    dayName
    -0.70
    GW
    -0.67
    /"
    -0.67
     Subtle
    -0.66
     LIMITED
    -0.66
    nex
    -0.66
    POSITIVE LOGITS
     critics
    1.36
     environmentalists
    1.28
     advocates
    1.24
     opponents
    1.23
     detractors
    1.22
     conservatives
    1.19
     proponents
    1.16
     campaigners
    1.15
     supporters
    1.14
     activists
    1.12
    Activations Density 0.319%

    No Known Activations