© 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. 3358
    Prev
    Next
    INDEX
    Explanations

    words related to basketball, sports statistics, and player performances

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

    expressions of hope or optimism

    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
     McGu
    -0.59
    imar
    -0.55
     Mayo
    -0.54
     Maj
    -0.54
    $$$$
    -0.53
     Haram
    -0.52
     payable
    -0.52
     msec
    -0.51
     Lloyd
    -0.51
     Bas
    -0.50
    POSITIVE LOGITS
    eful
    1.46
    ef
    1.30
    eless
    1.20
    efully
    1.19
    lite
    1.08
    sc
    0.98
    esy
    0.94
    along
    0.89
    kins
    0.85
    ew
    0.84
    Activations Density 0.025%

    No Known Activations