© 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. 3-RES-JB
    11. 10698
    Prev
    Next
    INDEX
    Explanations

    terms related to sociology

    oai_token-act-pair · gpt-3.5-turbo

    terminology and concepts related to sociology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Centauri
    -0.79
     spare
    -0.73
     Fallen
    -0.70
     Kavanaugh
    -0.69
     Everest
    -0.63
    warm
    -0.62
     Slayer
    -0.62
     Mattis
    -0.60
     Gemini
    -0.60
    bows
    -0.60
    POSITIVE LOGITS
    keye
    1.08
    ieties
    0.90
    iological
    0.89
    iologist
    0.87
    entric
    0.86
    reth
    0.84
    oro
    0.84
    iet
    0.83
    sych
    0.82
    agonists
    0.82
    Activations Density 0.008%

    No Known Activations