© 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. 24176
    Prev
    Next
    INDEX
    Explanations

    words related to the action of assigning tasks or responsibilities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "assign" and its variations in the context of decision-making processes

    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
    Ak
    -0.73
    FORE
    -0.73
    steen
    -0.70
    loo
    -0.65
    DOC
    -0.64
    behind
    -0.62
    sil
    -0.61
    ttp
    -0.61
    á½
    -0.60
    amsung
    -0.60
    POSITIVE LOGITS
     blame
    1.07
     duties
    0.95
     responsibility
    0.92
     tasks
    0.92
     responsibilities
    0.87
     allegiance
    0.82
     permissions
    0.81
    ments
    0.80
     quotas
    0.79
     priority
    0.78
    Activations Density 0.076%

    No Known Activations