© 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. 9782
    Prev
    Next
    INDEX
    Explanations

    references to outdated content

    oai_token-act-pair · gpt-3.5-turbo

    instances of outdated information

    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
    adra
    -0.76
    ovation
    -0.72
    wheel
    -0.69
    othy
    -0.68
    parent
    -0.67
    allel
    -0.63
    asin
    -0.62
    ALK
    -0.62
     ski
    -0.61
    swe
    -0.61
    POSITIVE LOGITS
    onday
    0.79
    SPONSORED
    0.68
     subscrib
    0.68
    Reloaded
    0.68
     notebooks
    0.67
     nodd
    0.66
     RPM
    0.66
     subscribed
    0.64
    tracks
    0.64
     Nost
    0.62
    Activations Density 0.000%

    No Known Activations