© 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. 9537
    Prev
    Next
    INDEX
    Explanations

    contractions of "does not" in text

    oai_token-act-pair · gpt-3.5-turbo

    the word "doesn't" in various contexts

    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
     DRAGON
    -0.71
     Dise
    -0.68
     ANG
    -0.65
    fox
    -0.65
     Remastered
    -0.63
     Mant
    -0.63
     Buff
    -0.62
    hung
    -0.61
     Ivory
    -0.60
    dar
    -0.60
    POSITIVE LOGITS
    't
    1.47
    kie
    0.93
    paces
    0.84
    berra
    0.78
    terness
    0.76
    ettings
    0.75
    ema
    0.74
    ajor
    0.74
    uts
    0.73
    ates
    0.73
    Activations Density 0.038%

    No Known Activations