Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 19396
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific places or entities associated with the term "Gateway" and "Bishop"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tac
    -0.84
    aqu
    -0.74
    âĹ
    -0.71
     tub
    -0.70
    cin
    -0.70
    liv
    -0.69
    Anim
    -0.69
    cry
    -0.69
     nap
    -0.68
    riages
    -0.68
    POSITIVE LOGITS
     Gateway
    2.11
     Bishop
    1.68
     gateway
    1.39
     Ras
    1.34
    oser
    1.25
     Hacker
    1.17
     Keller
    1.03
     Kinder
    1.00
     Kir
    0.98
     Cascade
    0.97
    Activations Density 0.033%

    No Known Activations