© 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
    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. 6790
    Prev
    Next
    INDEX
    Explanations

    verbs related to various activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal actions or experiences

    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
    quartered
    -0.72
    SPONSORED
    -0.70
    astical
    -0.68
    aptic
    -0.64
    soever
    -0.64
    ield
    -0.63
    wayne
    -0.60
    Alternatively
    -0.60
    generated
    -0.60
     forthcoming
    -0.60
    POSITIVE LOGITS
     alot
    1.11
     plenty
    0.96
     lots
    0.88
     yesterday
    0.88
     tons
    0.84
     mine
    0.79
     awhile
    0.77
     enough
    0.77
     quite
    0.75
     countless
    0.74
    Activations Density 0.433%

    No Known Activations