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. 10-RES-JB
    6. 23615
    Prev
    Next
    INDEX
    Explanations

    terms related to K-9 units and operations

    oai_token-act-pair · gpt-3.5-turbo

    references to 'K-pop' and related cultural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EntityItem
    -0.64
     wi
    -0.60
     aggrav
    -0.60
     bere
    -0.60
     revel
    -0.59
     Illum
    -0.59
     Pag
    -0.58
     WH
    -0.58
     unpre
    -0.58
     MOT
    -0.58
    POSITIVE LOGITS
    shaped
    1.32
    series
    1.11
    Day
    1.09
    Series
    1.06
    word
    1.06
    bomb
    1.05
    Spot
    1.03
    Town
    1.02
    level
    1.02
    rated
    1.01
    Activations Density 0.030%

    No Known Activations