© 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. 9-RES-JB
    11. 14074
    Prev
    Next
    INDEX
    Explanations

    references to information or updates

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to providing information or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.70
    Enlarge
    -0.67
     depreciation
    -0.62
    Ħ¢
    -0.62
     defic
    -0.60
    purpose
    -0.60
     plurality
    -0.60
    FontSize
    -0.59
    iasis
    -0.58
     surplus
    -0.57
    POSITIVE LOGITS
     Tickets
    0.92
    Tickets
    0.90
     teaser
    0.84
     UPDATE
    0.79
     synopsis
    0.79
     teased
    0.78
    istration
    0.77
     meantime
    0.76
    UPDATE
    0.75
     Pricing
    0.74
    Activations Density 0.607%

    No Known Activations