© 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. 0-RES-JB
    11. 1130
    Prev
    Next
    INDEX
    Explanations

    keywords related to assigning people to tasks, roles, or locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "assigned" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIDEOS
    -0.88
     Smile
    -0.72
    yip
    -0.72
    hhh
    -0.69
    Austral
    -0.66
    Wall
    -0.66
    laugh
    -0.64
     resurgence
    -0.63
     Thread
    -0.63
    ews
    -0.63
    POSITIVE LOGITS
     assigned
    3.64
     assign
    2.05
     assigns
    1.91
     allotted
    1.90
     assignment
    1.88
     assigning
    1.86
     assignments
    1.83
     allocated
    1.69
     delegated
    1.68
     designated
    1.51
    Activations Density 0.018%

    No Known Activations