© 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. 7413
    Prev
    Next
    INDEX
    Explanations

    situations related to healthcare and social services

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements related to personal circumstances and choices

    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
    olo
    -0.75
    Mer
    -0.74
    ESE
    -0.73
    BuyableInstoreAndOnline
    -0.65
    UC
    -0.65
    qua
    -0.64
    Ven
    -0.63
    rio
    -0.63
    MSN
    -0.63
    Pear
    -0.62
    POSITIVE LOGITS
     consequently
    1.15
     therefore
    1.13
     subsequently
    1.00
     consequ
    0.98
     thereby
    0.98
     somehow
    0.96
     nevertheless
    0.93
     thereafter
    0.90
     nonetheless
    0.87
     accompanying
    0.82
    Activations Density 0.490%

    No Known Activations