© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1808
    Prev
    Next
    INDEX
    Explanations

    information related to scientific measurements and analysis

    oai_token-act-pair · gpt-3.5-turbo

    scientific measurements and data related to environmental or climatic conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     Reggie
    -0.75
    Kids
    -0.73
     Stranger
    -0.71
     Shawn
    -0.70
     Xander
    -0.70
     Overse
    -0.69
    luaj
    -0.67
    selling
    -0.66
     Nicarag
    -0.65
    doctor
    -0.65
    POSITIVE LOGITS
     âμ
    1.63
     âī
    1.44
     ÎĶ
    1.40
     Î
    1.29
     μ
    1.29
     ±
    1.29
     âī¤
    1.25
     ÏĦ
    1.21
     equilibrium
    1.17
     (âĪĴ
    1.17
    Activations Density 0.437%

    No Known Activations