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. 22408
    Prev
    Next
    INDEX
    Explanations

    country names and companies/entities in conjunction with each other

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names related to organizations, countries, or notable figures

    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
    tains
    -0.75
    / 
    -0.70
     ±
    -0.64
     Learns
    -0.63
    and
    -0.62
     AND
    -0.61
     and
    -0.59
     &
    -0.59
     et
    -0.58
    "]=>
    -0.58
    POSITIVE LOGITS
     alike
    1.71
     are
    1.30
     respectively
    1.21
     were
    1.18
     aren
    1.16
     collide
    1.14
     weren
    1.10
     have
    1.08
     converge
    1.07
     differ
    1.07
    Activations Density 0.450%

    No Known Activations