© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 4113
    Prev
    Next
    INDEX
    Explanations

    mentions of specific brand names related to various products or services

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the term "Pet 2" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĹĺ
    -0.73
    mith
    -0.70
     seeded
    -0.67
    UME
    -0.67
    IDER
    -0.65
    xual
    -0.64
    ources
    -0.64
    IDES
    -0.62
     Reson
    -0.61
     doub
    -0.61
    POSITIVE LOGITS
    ertodd
    1.34
    abyte
    1.22
    roleum
    1.20
    rified
    1.17
    abytes
    1.16
    itions
    1.11
    unia
    1.08
    rol
    0.98
    rification
    0.97
    pet
    0.96
    Activations Density 0.044%

    No Known Activations