© 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. 10-RES-JB
    11. 4635
    Prev
    Next
    INDEX
    Explanations

    letter 's' appearing as a possessive marker

    oai_token-act-pair · gpt-3.5-turbo

    the word "that's" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fee
    -0.61
    éĹĺ
    -0.60
     Juda
    -0.59
    ousel
    -0.59
    ILE
    -0.57
     Orient
    -0.55
    iard
    -0.55
     Publications
    -0.55
    inav
    -0.55
    izons
    -0.55
    POSITIVE LOGITS
     why
    1.11
     gonna
    0.91
     okay
    0.90
     what
    0.88
     alright
    0.85
     exactly
    0.84
     happening
    0.82
     understandable
    0.81
     bullshit
    0.81
     impossible
    0.80
    Activations Density 0.063%

    No Known Activations