© 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. 5849
    Prev
    Next
    INDEX
    Explanations

    instances of the preposition "in" followed by different objects or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "come in" followed by various contexts or descriptions

    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
    DOM
    -0.71
    emis
    -0.67
     Talent
    -0.65
    llan
    -0.64
    cas
    -0.64
    tein
    -0.60
    istani
    -0.60
    âĢ¢âĢ¢
    -0.60
    KEN
    -0.59
    cia
    -0.58
    POSITIVE LOGITS
     handy
    1.52
    escap
    0.80
    offensive
    0.78
    versely
    0.77
     shapes
    0.77
     shades
    0.76
     dro
    0.75
     contact
    0.75
     spite
    0.74
     abundance
    0.74
    Activations Density 0.068%

    No Known Activations