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. 1-RES-JB
    6. 4321
    Prev
    Next
    INDEX
    Explanations

    keywords related to furniture or equipment such as "bed"

    oai_token-act-pair · gpt-3.5-turbo

    references to beds or sleeping arrangements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eclipse
    -0.66
     breeze
    -0.63
     concent
    -0.63
    abeth
    -0.63
     delicate
    -0.62
    olate
    -0.60
     Alps
    -0.58
    merce
    -0.58
     cac
    -0.58
    ITNESS
    -0.57
    POSITIVE LOGITS
    bed
    1.45
    bing
    1.01
    ford
    0.98
    ding
    0.98
    theless
    0.90
    bat
    0.86
    rock
    0.84
    dit
    0.84
    ded
    0.82
    rill
    0.82
    Activations Density 0.004%

    No Known Activations