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. 10953
    Prev
    Next
    INDEX
    Explanations

    technical terms related to various fields such as biology, technology, and mathematics

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and specific terms associated with biological or technical processes

    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
    pees
    -1.01
    aws
    -0.82
    wives
    -0.80
     Bullets
    -0.79
    leys
    -0.78
    pee
    -0.77
    famous
    -0.76
     Brothers
    -0.75
    Girls
    -0.75
    kees
    -0.74
    POSITIVE LOGITS
     consequ
    1.10
     other
    1.08
     optionally
    0.92
     hence
    0.91
     localization
    0.91
     modulation
    0.89
     visualization
    0.89
     mitigation
    0.89
     attendant
    0.89
     behavioural
    0.89
    Activations Density 0.250%

    No Known Activations