© 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. 2646
    Prev
    Next
    INDEX
    Explanations

    numbers followed by nouns expressing quantities

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

    articles indicating quantity or types of conditions

    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
    onis
    -0.71
    ATURES
    -0.67
    ola
    -0.64
    ORTS
    -0.63
    elli
    -0.63
    ody
    -0.63
    APTER
    -0.62
    imaru
    -0.62
    isodes
    -0.62
    eur
    -0.62
    POSITIVE LOGITS
     glance
    1.22
     distance
    0.98
     time
    0.86
     disadvantage
    0.82
     snail
    0.82
     fraction
    0.82
     later
    0.79
     rate
    0.76
     minimum
    0.76
     cost
    0.75
    Activations Density 0.078%

    No Known Activations