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. 11-RES-JB
    6. 10454
    Prev
    Next
    INDEX
    Explanations

    words related to the HIV virus and its impacts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to HIV and its impact on individuals and society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.84
    semble
    -0.78
    alty
    -0.75
    )=(
    -0.72
    gd
    -0.71
    books
    -0.70
    lying
    -0.70
    */(
    -0.67
    leigh
    -0.67
    pmwiki
    -0.66
    POSITIVE LOGITS
    AIDS
    1.34
     infection
    1.33
     infections
    1.21
     AIDS
    1.16
     epidemic
    1.14
     virus
    1.05
     disease
    1.04
     diagnosis
    1.01
     diagnoses
    1.01
    infect
    1.00
    Activations Density 0.026%

    No Known Activations