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. 17636
    Prev
    Next
    INDEX
    Explanations

    phrases related to rules and constraints

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to social norms and regulations

    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
    ideshow
    -0.31
    augh
    -0.31
    )</
    -0.30
    )."
    -0.29
     outwe
    -0.29
    entimes
    -0.29
    utm
    -0.29
     hers
    -0.29
     candy
    -0.28
    arer
    -0.28
    POSITIVE LOGITS
     Examination
    0.35
    galitarian
    0.33
    ombat
    0.31
     Whilst
    0.30
    raltar
    0.30
     Invalid
    0.30
     Wasteland
    0.29
     Regarding
    0.28
     Civilization
    0.28
     Dragons
    0.28
    Activations Density 3.587%

    No Known Activations