Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 9729
    Prev
    Next
    INDEX
    Explanations

    the phrase "the main."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the main story or important content in a document

    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
     Centauri
    -0.80
    »Ĵ
    -0.72
     Profession
    -0.70
     Metallic
    -0.69
     Benefit
    -0.69
    Ö¼
    -0.67
    NetMessage
    -0.66
    utenant
    -0.66
    ï¸ı
    -0.66
     Sparrow
    -0.63
    POSITIVE LOGITS
    stay
    0.84
     theme
    0.79
     source
    0.78
    ideshow
    0.75
     story
    0.73
     cartoons
    0.72
     cartoon
    0.70
     slideshow
    0.69
     gallery
    0.67
    stuff
    0.67
    Activations Density 0.016%

    No Known Activations