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. 23678
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific fictional or fantasy elements, such as "Orc", "Elf", and "Nec"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Necessity" and related concepts, especially 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
    Desk
    -0.80
    DERR
    -0.73
    ãģĦ
    -0.70
     reel
    -0.69
     caption
    -0.67
    zzle
    -0.66
    د
    -0.63
    Lens
    -0.62
     Oaks
    -0.62
     Advent
    -0.61
    POSITIVE LOGITS
    ersen
    1.01
    rast
    0.98
    ropy
    0.93
    stals
    0.92
    rob
    0.92
    rote
    0.90
    stall
    0.88
    erest
    0.88
    romancer
    0.87
    ulhu
    0.87
    Activations Density 0.042%

    No Known Activations