© 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. 11-RES-JB
    11. 14149
    Prev
    Next
    INDEX
    Explanations

    words related to administrative or organizational tasks, such as "s" which might indicate a plural possessive form

    oai_token-act-pair · gpt-3.5-turbo

    plural nouns referencing years

    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
    alias
    -0.62
    Entity
    -0.60
    adj
    -0.59
    bear
    -0.58
    CHAT
    -0.57
    ographer
    -0.57
     interacts
    -0.56
    sites
    -0.56
    wright
    -0.56
    æ©
    -0.56
    POSITIVE LOGITS
     anniversary
    1.01
     birthday
    0.89
     commencement
    0.88
     edition
    0.87
    aturdays
    0.83
     inaugural
    0.83
     busiest
    0.80
     festivities
    0.80
     hottest
    0.78
     maiden
    0.77
    Activations Density 0.062%

    No Known Activations