Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 16855
    Prev
    Next
    INDEX
    Explanations

    evidence or references to the presence or properties of liquid substances

    oai_token-act-pair · gpt-3.5-turbo

    references to liquid substances or liquids

    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
    reon
    -0.79
    BOOK
    -0.77
    ths
    -0.66
    oÄŁ
    -0.66
     Shattered
    -0.64
    shire
    -0.63
    otle
    -0.62
    udeb
    -0.62
     Celebr
    -0.61
    scoring
    -0.61
    POSITIVE LOGITS
     nitrogen
    1.14
    ation
    0.88
    ated
    0.85
     helium
    0.85
     cooled
    0.83
    itate
    0.83
     eyel
    0.82
     propell
    0.81
    ators
    0.81
     cooling
    0.80
    Activations Density 0.052%

    No Known Activations