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. 0-RES-JB
    6. 17562
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or titles

    oai_token-act-pair · gpt-3.5-turbo

    specific names and terms related to people or entities, particularly in legal or academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alger
    -0.88
     Yemen
    -0.81
     Yemeni
    -0.78
     Algeria
    -0.76
    egal
    -0.67
    213
    -0.66
    Ń
    -0.65
     Slash
    -0.65
    aeda
    -0.64
    ALD
    -0.64
    POSITIVE LOGITS
     Pok
    1.85
     Pom
    1.60
     Pik
    1.54
     Pon
    1.52
     Pere
    1.46
     Pike
    1.43
    PN
    1.43
     PP
    1.41
     P
    1.40
     Pine
    1.39
    Activations Density 0.082%

    No Known Activations