© 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. 7-RES-JB
    11. 23408
    Prev
    Next
    INDEX
    Explanations

    instances where the action of "taking" something is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "take" and its variations indicating various actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holm
    -0.67
    eers
    -0.66
    Cong
    -0.62
    ese
    -0.62
    eman
    -0.61
     collapsing
    -0.61
     dissatisf
    -0.61
     agre
    -0.61
    ingen
    -0.60
    ulo
    -0.58
    POSITIVE LOGITS
    aways
    1.20
     advantage
    1.18
     care
    1.00
     refuge
    0.93
     heed
    0.93
     aback
    0.92
     precautions
    0.87
    overs
    0.85
    away
    0.85
    autions
    0.82
    Activations Density 0.116%

    No Known Activations