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. 7-RES-JB
    6. 2558
    Prev
    Next
    INDEX
    Explanations

    the word "hundreds" within the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hundreds" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Situation
    -0.66
    estine
    -0.63
     hegemony
    -0.62
    agate
    -0.60
     symmetry
    -0.59
    inventoryQuantity
    -0.58
    igion
    -0.56
     menace
    -0.56
     Manifest
    -0.55
    shit
    -0.55
    POSITIVE LOGITS
    ourcing
    1.04
     thousand
    0.93
    ourced
    0.92
    paces
    0.91
    eenth
    0.87
    entimes
    0.87
    uously
    0.84
     thousands
    0.83
    ousands
    0.80
    uous
    0.79
    Activations Density 0.035%

    No Known Activations