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. 7854
    Prev
    Next
    INDEX
    Explanations

    political and ideological terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political ideologies and social movements

    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
     guiName
    -0.61
    onen
    -0.58
    é¾į
    -0.53
    20439
    -0.51
     Passage
    -0.51
     Piper
    -0.51
     Mous
    -0.51
    lyak
    -0.49
     Nich
    -0.49
     Kubrick
    -0.48
    POSITIVE LOGITS
     etc
    1.25
    etc
    0.86
    â̦)
    0.82
    whatever
    0.78
     ect
    0.70
    â̦
    0.61
    cheat
    0.60
    doms
    0.59
     â̦
    0.59
     gal
    0.57
    Activations Density 0.561%

    No Known Activations