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. 0-RES-JB
    6. 19554
    Prev
    Next
    INDEX
    Explanations

    texts related to the flow or movement of something

    oai_token-act-pair · gpt-3.5-turbo

    references to continuous movement or transfer of material or energy

    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
    rely
    -0.64
    Surv
    -0.64
    ile
    -0.61
    teen
    -0.61
    ARCH
    -0.61
    ogen
    -0.61
     KD
    -0.60
     Kessler
    -0.60
     Diagn
    -0.59
    nos
    -0.59
    POSITIVE LOGITS
     flowing
    3.73
     flowed
    2.34
     flows
    1.87
     flow
    1.67
     swirling
    1.44
     pouring
    1.37
     emanating
    1.30
     dripping
    1.26
    flows
    1.22
     surging
    1.20
    Activations Density 0.018%

    No Known Activations