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. 24471
    Prev
    Next
    INDEX
    Explanations

    phrases related to a mix of technical and scientific topics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to education, technology, and governance

    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
     iT
    -0.65
     Kaplan
    -0.63
    oret
    -0.63
    abase
    -0.62
    wordpress
    -0.62
     Osc
    -0.60
    birth
    -0.60
    javascript
    -0.59
    adobe
    -0.59
    mone
    -0.58
    POSITIVE LOGITS
     alike
    2.00
     respectively
    1.99
    depending
    1.10
     collide
    0.90
    hips
    0.89
     interchange
    0.88
     depending
    0.87
     together
    0.85
     jointly
    0.85
     simultaneously
    0.84
    Activations Density 0.633%

    No Known Activations