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. 15387
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences indicating a consequential event or action

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods at the end of sentences

    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
    thal
    -0.79
    itan
    -0.73
    pecially
    -0.72
    tones
    -0.70
    eatured
    -0.70
    culus
    -0.70
    cipled
    -0.69
    yssey
    -0.67
     pit
    -0.67
    ior
    -0.67
    POSITIVE LOGITS
     Eventually
    1.18
     Again
    1.06
     Then
    1.06
     Later
    1.05
     And
    1.04
     Soon
    1.03
     Ultimately
    1.01
     Slowly
    1.00
     But
    1.00
     Literally
    0.99
    Activations Density 0.794%

    No Known Activations