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. 6-RES-JB
    6. 16259
    Prev
    Next
    INDEX
    Explanations

    verbs related to cooking techniques

    oai_token-act-pair · gpt-3.5-turbo

    words associated with cooking methods and actions related to uncovering or revealing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ULTS
    -0.74
    CHR
    -0.64
    cius
    -0.63
     Nare
    -0.63
     injunction
    -0.60
    Ear
    -0.58
    ULT
    -0.57
    USE
    -0.56
    EAR
    -0.56
     ACTION
    -0.56
    POSITIVE LOGITS
    ing
    2.65
    ership
    1.30
    edIn
    1.23
    ING
    1.23
    ingham
    1.21
    eering
    1.20
    ging
    1.18
    itives
    1.17
    ings
    1.12
    ions
    1.11
    Activations Density 0.231%

    No Known Activations