Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 18685
    Prev
    Next
    INDEX
    Explanations

    references to different countries or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to countries and their characteristics or situations

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

    No Comments

    Negative Logits
    alion
    -0.70
     Horus
    -0.70
     Wife
    -0.69
    ãĥĺ
    -0.67
     girlfriend
    -0.65
    cade
    -0.64
     poem
    -0.64
     himself
    -0.63
     Booster
    -0.61
     Scarlett
    -0.60
    POSITIVE LOGITS
     respectively
    0.92
     territ
    0.84
     converge
    0.84
    ortium
    0.84
     alike
    0.84
     contiguous
    0.83
     territories
    0.83
     geographically
    0.82
     acad
    0.81
     arsen
    0.79
    Activations Density 1.140%

    No Known Activations