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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7847
    Prev
    Next
    INDEX
    Explanations

    the word "dry" along with its descriptor

    oai_token-act-pair · gpt-3.5-turbo

    references to dryness or dry conditions

    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
    CVE
    -0.81
    ority
    -0.78
    aurus
    -0.73
    ĸļ
    -0.71
    emonium
    -0.69
    ————
    -0.69
    awaru
    -0.66
     Haley
    -0.66
    inez
    -0.66
    utory
    -0.65
    POSITIVE LOGITS
    wall
    1.20
    ness
    0.96
     erase
    0.86
    lands
    0.84
    lock
    0.81
    tight
    0.80
    clean
    0.80
     cleaners
    0.80
    ads
    0.79
    locks
    0.79
    Activations Density 0.038%

    No Known Activations