© 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. 2-RES-JB
    11. 21778
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various settings and characters in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific actor or character named "Hod" in the context of various narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leone
    -0.74
    USE
    -0.72
    IZE
    -0.71
    anwhile
    -0.69
    _>
    -0.65
     Canaver
    -0.64
    INTER
    -0.64
    Leader
    -0.64
     Wonderland
    -0.62
    ISTER
    -0.62
    POSITIVE LOGITS
    yssey
    1.18
    rod
    1.09
     Hod
    1.05
    rys
    0.98
    bard
    0.98
    wig
    0.97
    sworth
    0.97
    ryn
    0.95
    rick
    0.93
    bage
    0.92
    Activations Density 0.008%

    No Known Activations