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

    Neuronpedia

    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. 9-RES-JB
    11. 4314
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases starting with "of" and containing a possessive pronoun

    oai_token-act-pair · gpt-3.5-turbo
    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
    NetMessage
    -0.86
    emis
    -0.79
    sonian
    -0.78
    ngth
    -0.77
    nown
    -0.73
    enth
    -0.68
    QL
    -0.66
    dayName
    -0.65
    BIL
    -0.65
    ··
    -0.65
    POSITIVE LOGITS
     truck
    0.73
     Jeep
    0.67
     pickup
    0.67
    ruck
    0.66
     Rampage
    0.66
    unts
    0.66
     wagon
    0.65
    pu
    0.65
     Toyota
    0.64
     jersey
    0.64
    Activations Density 0.055%

    No Known Activations