© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13256
    Prev
    Next
    INDEX
    Explanations

    references to countries and international organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to international entities and geopolitical terms

    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
    liest
    -0.92
    agame
    -0.88
    iest
    -0.87
    icter
    -0.83
    osphere
    -0.82
    est
    -0.80
    ossibility
    -0.78
    ppings
    -0.74
    eful
    -0.73
    onies
    -0.73
    POSITIVE LOGITS
    edIn
    0.76
     Canaveral
    0.69
     violations
    0.68
    åĨ
    0.67
    é¾įå¥ij士
    0.66
     practition
    0.66
     citiz
    0.60
     commitments
    0.60
     behavi
    0.60
     wise
    0.59
    Activations Density 0.633%

    No Known Activations