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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 12296
    Prev
    Next
    INDEX
    Explanations

    terms related to sorcery and specific names like Voronenkov and Korver

    oai_token-act-pair · gpt-3.5-turbo

    references to "sorcery" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITNESS
    -0.78
     Reloaded
    -0.75
    ichick
    -0.73
    ä¹ĭ
    -0.69
     Gutenberg
    -0.68
    yrinth
    -0.66
     Palmer
    -0.66
    icted
    -0.64
    ruary
    -0.62
    ravings
    -0.62
    POSITIVE LOGITS
    cery
    1.16
     Sor
    1.15
    ority
    1.03
    ashtra
    0.85
     ILCS
    0.84
     sor
    0.83
    vine
    0.79
    cha
    0.79
     tyr
    0.78
     obser
    0.78
    Activations Density 0.007%

    No Known Activations