© 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. 8-RES-JB
    11. 18521
    Prev
    Next
    INDEX
    Explanations

    terms related to superlatives

    oai_token-act-pair · gpt-3.5-turbo

    words and variations of the prefix "super."

    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
     omission
    -0.70
     Shepard
    -0.61
    ĸļ
    -0.61
    PLA
    -0.58
     Byrd
    -0.58
    deen
    -0.58
    BUS
    -0.58
     NEC
    -0.58
     Friedman
    -0.58
     bleed
    -0.58
    POSITIVE LOGITS
    rencies
    0.89
    uctor
    0.87
    heses
    0.86
    roid
    0.82
    anium
    0.80
    olester
    0.80
    ioxid
    0.77
    hesis
    0.76
    mega
    0.76
    omial
    0.75
    Activations Density 0.103%

    No Known Activations