© 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. 9841
    Prev
    Next
    INDEX
    Explanations

    organizations and institutions followed by descriptions of their activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "is" and related content about organizations or entities

    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
     slips
    -0.72
    pered
    -0.72
    ukong
    -0.72
     temptation
    -0.69
    ses
    -0.66
     scenarios
    -0.65
    ourt
    -0.65
    luster
    -0.64
    asser
    -0.63
     shocks
    -0.63
    POSITIVE LOGITS
     headquartered
    1.59
     sponsoring
    1.34
     affiliated
    1.30
     staffed
    1.30
     founded
    1.24
     owned
    1.17
     disbanded
    1.15
    affiliated
    1.13
     nonpartisan
    1.11
     comprised
    1.11
    Activations Density 0.205%

    No Known Activations