© 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. 14311
    Prev
    Next
    INDEX
    Explanations

    references to the social media platform Instagram

    oai_token-act-pair · gpt-3.5-turbo

    references to the social media platform Instagram

    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
    inelli
    -0.78
     Hond
    -0.72
     Booker
    -0.72
    Beg
    -0.65
     Refresh
    -0.62
     Norwich
    -0.61
    âĨ
    -0.61
    Dim
    -0.60
    ELY
    -0.60
     Nicarag
    -0.60
    POSITIVE LOGITS
    agram
    1.25
    matical
    0.86
    bender
    0.82
    uration
    0.82
    matically
    0.79
    mite
    0.75
    inx
    0.75
    matic
    0.74
    tags
    0.72
    tips
    0.72
    Activations Density 0.011%

    No Known Activations