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. 311
    Prev
    Next
    INDEX
    Explanations

    words related to increasing or enhancing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "increase."

    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
    ician
    -0.72
    aries
    -0.70
     Healer
    -0.69
     Bowman
    -0.67
    mates
    -0.67
     ¯
    -0.66
     Monstrous
    -0.65
    icians
    -0.65
    gets
    -0.65
    ··
    -0.64
    POSITIVE LOGITS
     exponentially
    0.99
    xual
    0.89
     awareness
    0.88
     subsequ
    0.88
     amounts
    0.85
     visibility
    0.82
     materially
    0.82
     likelihood
    0.82
     sidx
    0.81
    imar
    0.79
    Activations Density 0.050%

    No Known Activations