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. 8-RES-JB
    6. 4386
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions that cause a change or reversal

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "versus" used in various contexts

    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
     conversion
    -0.65
    ãĥ¼ãĥĨ
    -0.64
    CHR
    -0.63
     Slater
    -0.62
    bed
    -0.59
    Reviewer
    -0.59
     wars
    -0.58
    fish
    -0.57
     nom
    -0.57
    TEXTURE
    -0.56
    POSITIVE LOGITS
    atile
    1.53
    atility
    1.42
    hip
    1.30
    erver
    1.18
    ippi
    1.10
    ibilities
    1.07
    ational
    1.07
    ystem
    1.07
    ullivan
    1.06
    chool
    1.03
    Activations Density 0.056%

    No Known Activations