© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 4720
    Prev
    Next
    INDEX
    Explanations

    mentions of hybrid cars

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

    references to hybrid technology or vehicles

    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
     gulf
    -0.64
     captcha
    -0.63
     CTR
    -0.62
     mole
    -0.59
     unknown
    -0.58
    âĶĢâĶĢ
    -0.58
     interchange
    -0.58
     almonds
    -0.58
     louder
    -0.57
     scratching
    -0.57
    POSITIVE LOGITS
    giene
    1.55
    brids
    1.42
    undai
    1.23
    brid
    1.22
    annis
    1.19
    bris
    1.17
    pert
    1.13
    rule
    1.12
    atts
    1.11
    genic
    1.10
    Activations Density 0.007%

    No Known Activations