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. 0-RES-JB
    6. 8869
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'ambient'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to patients and medical contexts

    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
     rape
    -0.67
     shoulder
    -0.66
     defenses
    -0.65
     Copyright
    -0.64
     revision
    -0.63
     support
    -0.62
     membership
    -0.61
     copyright
    -0.61
     numbered
    -0.61
     AGA
    -0.61
    POSITIVE LOGITS
    ient
    4.90
    ients
    2.93
    iency
    2.47
    ience
    2.20
    iences
    1.71
    iens
    1.62
    IENT
    1.59
    iment
    1.48
    iencies
    1.40
    iments
    1.33
    Activations Density 0.016%

    No Known Activations