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. 1007
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences emphasizing priority or importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the importance or priority of specific concepts or actions

    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
    Lyn
    -0.78
    chrom
    -0.75
    udging
    -0.74
    fell
    -0.71
    pmwiki
    -0.70
    nan
    -0.68
    iots
    -0.67
    thur
    -0.66
    employment
    -0.66
    arter
    -0.66
    POSITIVE LOGITS
     foremost
    1.01
     among
    0.77
     amongst
    0.77
    tenance
    0.75
     importance
    0.75
    entimes
    0.74
     focuses
    0.67
    warts
    0.66
     concerning
    0.66
     priority
    0.65
    Activations Density 0.023%

    No Known Activations