© 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. 2707
    Prev
    Next
    INDEX
    Explanations

    specific keywords related to legal and organizational terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to governmental and institutional structures or processes

    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
    theless
    -1.00
    etheless
    -0.82
     goblins
    -0.78
     upside
    -0.77
    anwhile
    -0.76
     oneself
    -0.76
     rumors
    -0.75
     broccoli
    -0.74
     altogether
    -0.72
     sprung
    -0.72
    POSITIVE LOGITS
    artment
    1.12
    istries
    1.05
    ilitation
    1.00
    Course
    1.00
    ository
    0.99
    achment
    0.97
    mination
    0.94
    ureau
    0.94
    iciency
    0.93
    folio
    0.92
    Activations Density 0.233%

    No Known Activations