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. 8-RES-JB
    6. 22133
    Prev
    Next
    INDEX
    Explanations

    phrases related to impactful or important statements

    oai_token-act-pair · gpt-3.5-turbo

    sentences that contain strong emotional statements or reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respectively
    -0.86
     remaining
    -0.79
     wet
    -0.77
     allowance
    -0.77
     touring
    -0.76
     manageable
    -0.74
     overall
    -0.70
     separately
    -0.70
     minim
    -0.70
     rigorous
    -0.70
    POSITIVE LOGITS
     Called
    1.45
     Something
    1.16
     Someone
    1.12
     Specifically
    1.01
     Suppose
    0.98
     Somebody
    0.97
     Referred
    0.96
     Apparently
    0.95
    Someone
    0.95
     Intent
    0.93
    Activations Density 0.619%

    No Known Activations