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. 7309
    Prev
    Next
    INDEX
    Explanations

    personal expressions of introspection and sharing personal experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal growth and positive sentiments

    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
     ÂŃ
    -0.74
    ÂŃ
    -0.64
     Rodham
    -0.62
    SPONSORED
    -0.60
     "'
    -0.60
     constit
    -0.58
     imper
    -0.57
    alions
    -0.57
    Enlarge
    -0.55
     Osama
    -0.55
    POSITIVE LOGITS
     hopefully
    0.70
    nesday
    0.68
     alot
    0.68
     honestly
    0.68
     downside
    0.66
     anyways
    0.66
     Sakuya
    0.66
    cember
    0.66
     Conclusion
    0.65
    DK
    0.64
    Activations Density 1.603%

    No Known Activations