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. 0-RES-JB
    6. 7291
    Prev
    Next
    INDEX
    Explanations

    verbs ending in 'ifies'

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate validation or confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stick
    -0.59
     feat
    -0.59
     sticking
    -0.58
     pint
    -0.57
     tattoo
    -0.57
     Tow
    -0.56
     ty
    -0.55
     Tour
    -0.55
     hanging
    -0.55
     du
    -0.54
    POSITIVE LOGITS
    ifies
    4.34
    ify
    2.29
    ifying
    2.14
    ified
    2.12
    ifications
    2.03
    ification
    2.03
    ifiers
    2.02
    IFIED
    1.92
    ifier
    1.91
    izes
    1.74
    Activations Density 0.014%

    No Known Activations