© 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. 22420
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or details

    oai_token-act-pair · gpt-3.5-turbo

    specific details and instructions related to events or transactions

    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
    igr
    -0.64
    naire
    -0.62
     shares
    -0.60
    views
    -0.58
    Attempts
    -0.57
    Myth
    -0.55
    UCT
    -0.55
    asses
    -0.54
    profile
    -0.54
     struggles
    -0.53
    POSITIVE LOGITS
     abound
    1.45
     are
    1.39
     aren
    1.29
     ARE
    1.13
     weren
    1.11
     were
    1.06
     vary
    1.02
     apply
    1.01
     await
    1.01
     arrive
    0.99
    Activations Density 0.313%

    No Known Activations