© 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. 15655
    Prev
    Next
    INDEX
    Explanations

    adverbs that emphasize a complete difference or contrast

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating totality or completeness

    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
    nings
    -0.81
    ity
    -0.67
    ulative
    -0.66
    olester
    -0.63
    ulators
    -0.62
    hao
    -0.62
    roe
    -0.61
    crow
    -0.61
    shows
    -0.60
     Commissioner
    -0.60
    POSITIVE LOGITS
     reliant
    0.90
    heartedly
    0.77
    opathic
    0.75
     predictable
    0.71
    BuyableInstoreAndOnline
    0.71
     dependent
    0.71
     comprised
    0.70
     conject
    0.70
     unlike
    0.70
     composed
    0.69
    Activations Density 0.028%

    No Known Activations