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. 15905
    Prev
    Next
    INDEX
    Explanations

    instances of the word "multiple"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "multiple."

    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
    spring
    -0.73
    roit
    -0.70
    NER
    -0.70
    Prince
    -0.69
    hers
    -0.68
    OST
    -0.66
    potion
    -0.66
    kamp
    -0.66
    IER
    -0.66
    ampunk
    -0.66
    POSITIVE LOGITS
     sclerosis
    1.38
    xes
    1.34
     iterations
    1.12
     simultaneous
    1.03
     generations
    0.97
    iating
    0.94
     overlapping
    0.93
     instances
    0.92
     layers
    0.89
     digits
    0.89
    Activations Density 0.030%

    No Known Activations