© 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. 22512
    Prev
    Next
    INDEX
    Explanations

    phrases related to roles and responsibilities in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to roles and responsibilities in various contexts

    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
    olen
    -0.74
    album
    -0.73
    izarre
    -0.71
    mares
    -0.69
    cies
    -0.69
    pleted
    -0.68
    videos
    -0.67
    sbm
    -0.65
    ertation
    -0.65
    ancies
    -0.64
    POSITIVE LOGITS
     protector
    1.46
     intermediary
    1.41
     conduit
    1.39
     facilit
    1.38
     guarant
    1.34
     watchdog
    1.34
     arbit
    1.31
     guardian
    1.31
     catalyst
    1.25
     medi
    1.24
    Activations Density 0.309%

    No Known Activations