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

    Neuronpedia

    Jacobian LensNEW
    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. 3927
    Prev
    Next
    INDEX
    Explanations

    terms related to something showing great potential or likelihood of success

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating high potential or optimism in various contexts

    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
    FactoryReloaded
    -0.77
    aida
    -0.76
    illon
    -0.73
    ighed
    -0.73
    avia
    -0.72
    cest
    -0.68
    pel
    -0.67
    cation
    -0.66
    ento
    -0.65
    ophobia
    -0.65
    POSITIVE LOGITS
     promising
    0.96
     prospects
    0.94
    ly
    0.87
     promises
    0.80
     cannabin
    0.78
     unden
    0.76
     antioxid
    0.73
     promise
    0.72
    NESS
    0.69
     strugg
    0.67
    Activations Density 0.010%

    No Known Activations