© 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. 6-RES-JB
    11. 23853
    Prev
    Next
    INDEX
    Explanations

    phrases where someone is publicly criticizing or denouncing someone or something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "called out"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olars
    -0.83
    ettlement
    -0.66
     gamble
    -0.65
     govern
    -0.64
     weap
    -0.63
     princip
    -0.63
    parable
    -0.63
    ushima
    -0.62
     ascend
    -0.62
     tastes
    -0.62
    POSITIVE LOGITS
    stretched
    1.11
     loud
    0.90
    casts
    0.86
    wards
    0.81
    dated
    0.79
    fitted
    0.74
    tical
    0.73
    posts
    0.72
    lier
    0.70
     loudly
    0.70
    Activations Density 0.016%

    No Known Activations