© 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. 8-RES-JB
    11. 17849
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a high likelihood or strong possibility

    oai_token-act-pair · gpt-3.5-turbo

    intensifying adverbs that convey strong certainty or likelihood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.68
     Prep
    -0.58
    oresc
    -0.58
     notebooks
    -0.57
    Frag
    -0.57
     Sands
    -0.56
    Mich
    -0.56
     Ending
    -0.56
    icative
    -0.55
     joking
    -0.55
    POSITIVE LOGITS
    rouse
    1.16
    venge
    1.01
    lege
    0.94
    ivably
    0.87
    activate
    0.84
    etheless
    0.81
    ceive
    0.80
    rely
    0.79
    own
    0.78
    ually
    0.76
    Activations Density 0.157%

    No Known Activations