© 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. 7-RES-JB
    11. 5151
    Prev
    Next
    INDEX
    Explanations

    words that indicate actions or decisions being taken

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "take" in various contexts

    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
     agre
    -0.74
    oad
    -0.70
    Cong
    -0.70
    holm
    -0.69
    tl
    -0.64
     accompanies
    -0.63
    nesses
    -0.62
    tx
    -0.62
    ler
    -0.62
    ese
    -0.61
    POSITIVE LOGITS
     advantage
    1.16
    aways
    1.06
     aback
    0.97
     heed
    0.87
     care
    0.85
     precedence
    0.81
    ²
    0.80
    ©¶æ
    0.80
     pains
    0.80
    OVER
    0.79
    Activations Density 0.110%

    No Known Activations