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. 18064
    Prev
    Next
    INDEX
    Explanations

    ingredients in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    ingredients and body parts mentioned in various contexts

    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
    cipled
    -0.68
     hindsight
    -0.59
    arak
    -0.55
    Adds
    -0.54
     Balk
    -0.54
    rend
    -0.53
     Competitive
    -0.52
     Intervention
    -0.51
     leaps
    -0.50
    think
    -0.50
    POSITIVE LOGITS
     belongings
    0.82
    respective
    0.70
     contents
    0.69
    anwhile
    0.68
     whereabouts
    0.66
     occupants
    0.65
     stored
    0.64
     respectively
    0.63
     occupied
    0.61
     possessions
    0.61
    Activations Density 0.772%

    No Known Activations