© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10163
    Prev
    Next
    INDEX
    Explanations

    phrases related to shutting down or closing operations or facilities

    oai_token-act-pair · gpt-3.5-turbo

    references to shutting down or disabling facilities, particularly in a governmental or industrial context

    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
    arov
    -0.73
    present
    -0.72
    older
    -0.72
    autions
    -0.71
    verages
    -0.70
     Guests
    -0.69
    venants
    -0.68
    Ĭ±
    -0.68
     commitments
    -0.68
    imon
    -0.66
    POSITIVE LOGITS
     consulate
    1.21
     hotline
    1.06
     embassy
    1.05
     DMV
    1.02
     laboratories
    1.01
     bookstore
    0.96
     postal
    0.93
     broadcaster
    0.92
     clinic
    0.92
     library
    0.92
    Activations Density 0.510%

    No Known Activations