© 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. 1039
    Prev
    Next
    INDEX
    Explanations

    instances where actions or events are being described

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating capability or permission

    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
    theless
    -0.67
     contingency
    -0.67
     revisions
    -0.65
     additions
    -0.64
     postponed
    -0.63
    soever
    -0.63
     alliances
    -0.62
     Lever
    -0.62
     Tend
    -0.62
     conduc
    -0.62
    POSITIVE LOGITS
     hear
    1.32
     see
    1.28
     faintly
    1.23
     smell
    1.23
     glimpse
    1.19
     discern
    1.17
     detect
    1.10
    see
    1.10
     SEE
    1.05
     perceive
    1.03
    Activations Density 0.162%

    No Known Activations