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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 24193
    Prev
    Next
    INDEX
    Explanations

    medical terms and data related to physiological conditions and research

    oai_token-act-pair · gpt-3.5-turbo

    references to medical conditions and characteristics related to psychiatric disorders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TextColor
    -0.79
     whim
    -0.74
    Days
    -0.72
     brim
    -0.71
     yours
    -0.70
     Armageddon
    -0.69
     dirt
    -0.69
    VPN
    -0.69
     Parkway
    -0.69
     wont
    -0.68
    POSITIVE LOGITS
     âμ
    1.36
     endogenous
    1.12
     methodological
    1.09
     quantitative
    1.08
     hypothesized
    1.06
     clinical
    1.04
     phenotype
    1.04
     clinically
    1.04
     causal
    1.03
     (âĪĴ
    1.02
    Activations Density 0.895%

    No Known Activations