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. 8-RES-JB
    6. 21403
    Prev
    Next
    INDEX
    Explanations

    information related to biology, genetics, and research findings

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific findings and hypotheses related to gender and biological mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udeb
    -0.75
    Company
    -0.74
    Street
    -0.71
    phabet
    -0.71
    zan
    -0.69
    grim
    -0.68
    apest
    -0.68
     bombed
    -0.68
    bare
    -0.67
    lance
    -0.67
    POSITIVE LOGITS
     biologically
    1.35
     genes
    1.22
     epigen
    1.21
     evolutionary
    1.21
     causal
    1.20
     biomark
    1.19
     caus
    1.17
     genetic
    1.15
     causation
    1.12
     mechanisms
    1.10
    Activations Density 0.593%

    No Known Activations