© 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. 3227
    Prev
    Next
    INDEX
    Explanations

    images from Getty with a specific focus on a particular topic or event

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

    visual references or images associated with events or items

    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
     44
    -0.80
     1954
    -0.77
     54
    -0.77
     154
    -0.76
     444
    -0.74
    antry
    -0.72
     1904
    -0.71
    terday
    -0.71
     174
    -0.70
     451
    -0.70
    POSITIVE LOGITS
    7
    1.06
    727
    0.86
     Seventh
    0.84
    707
    0.81
    77
    0.77
    713
    0.76
    677
    0.76
    747
    0.74
    Ŀ
    0.73
    Ĭ±
    0.73
    Activations Density 0.089%

    No Known Activations