© 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. 16777
    Prev
    Next
    INDEX
    Explanations

    phrases indicating clarity or certainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing clarity and certainty

    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
    aughs
    -0.81
    rella
    -0.71
    psey
    -0.70
    eries
    -0.70
    «ĺ
    -0.65
    Subscribe
    -0.60
     Lynd
    -0.60
    enium
    -0.60
    untarily
    -0.59
    lymp
    -0.59
    POSITIVE LOGITS
     unlaw
    0.85
    CHAT
    0.80
     unamb
    0.79
     unmist
    0.75
     actionGroup
    0.75
     boundaries
    0.74
     deline
    0.72
     outlines
    0.71
     intent
    0.70
     territory
    0.68
    Activations Density 0.222%

    No Known Activations