© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 12780
    Prev
    Next
    INDEX
    Explanations

    references to conflicts of interest in research publications

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to academic research and publication processes

    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
    gamer
    -0.87
    terday
    -0.68
    demand
    -0.66
     Hardcore
    -0.66
    ioxide
    -0.66
     mall
    -0.66
    Redd
    -0.65
    okemon
    -0.64
    iddler
    -0.63
     evict
    -0.63
    POSITIVE LOGITS
     manuscript
    1.45
     Authors
    1.26
    uscript
    1.18
     PubMed
    1.14
     authors
    1.13
    authors
    1.13
     manuscripts
    1.11
     Publication
    1.11
    Study
    1.08
     Supplementary
    1.07
    Activations Density 0.174%

    No Known Activations