© 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. 2-RES-JB
    11. 4459
    Prev
    Next
    INDEX
    Explanations

    controversial topics or events

    oai_token-act-pair · gpt-3.5-turbo

    the term "controversy" and its related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odes
    -0.80
    berman
    -0.75
    ingers
    -0.74
    lasses
    -0.73
    vae
    -0.72
    ells
    -0.68
    onz
    -0.67
    thening
    -0.66
    amina
    -0.66
    ourke
    -0.65
    POSITIVE LOGITS
     controversy
    1.04
     controversies
    0.95
    naire
    0.94
     shroud
    0.83
    naires
    0.81
     uproar
    0.80
     involving
    0.80
     flared
    0.78
     revolving
    0.78
     arises
    0.77
    Activations Density 0.013%

    No Known Activations