© 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. 12-RES-JB
    11. 4629
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and networking

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to significant events or developments, particularly in a narrative or analytical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    IAN
    -0.53
    nosis
    -0.53
    mbuds
    -0.53
    Privacy
    -0.48
     readiness
    -0.48
    ADRA
    -0.48
     compliance
    -0.46
    llah
    -0.46
     hostility
    -0.45
    rics
    -0.45
    POSITIVE LOGITS
     from
    1.19
    from
    1.01
     From
    0.95
     FROM
    0.95
    From
    0.86
     fro
    0.69
     off
    0.61
     to
    0.57
     of
    0.57
     away
    0.55
    Activations Density 0.511%

    No Known Activations