© 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. 10-RES-JB
    11. 21511
    Prev
    Next
    INDEX
    Explanations

    words related to marketing and promotion

    oai_token-act-pair · gpt-3.5-turbo

    terms related to publicity and hype

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.83
    arre
    -0.70
    radical
    -0.64
    WER
    -0.63
    tre
    -0.63
    REE
    -0.62
    artment
    -0.61
    sonian
    -0.61
    abus
    -0.57
    cible
    -0.57
    POSITIVE LOGITS
     bestowed
    1.07
    seekers
    0.99
     fades
    0.98
     surrounding
    0.94
     afforded
    0.93
     seekers
    0.90
     stunts
    0.88
    seeking
    0.87
     tremend
    0.85
     endorsements
    0.83
    Activations Density 0.129%

    No Known Activations