© 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. 11-RES-JB
    11. 13484
    Prev
    Next
    INDEX
    Explanations

    contractions with an apostrophe followed by 's'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "it's" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naires
    -0.76
    aviour
    -0.69
    arian
    -0.59
    mob
    -0.59
    volent
    -0.58
    ribution
    -0.58
     devise
    -0.58
    orde
    -0.58
    disabled
    -0.58
    ective
    -0.57
    POSITIVE LOGITS
     tempting
    0.90
     undeniable
    0.87
    aturday
    0.86
     ironic
    0.85
     amazing
    0.81
     dawn
    0.81
     impossible
    0.79
     easy
    0.79
     raining
    0.79
    estern
    0.79
    Activations Density 0.128%

    No Known Activations