Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 18047
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the most important aspect or priority

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the importance or priority of certain topics or elements

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

    No Comments

    Negative Logits
    chrom
    -0.81
    Lyn
    -0.76
     skelet
    -0.71
    fell
    -0.69
    iots
    -0.68
    hex
    -0.67
    udging
    -0.66
    nan
    -0.66
    eries
    -0.65
    riages
    -0.65
    POSITIVE LOGITS
     foremost
    1.10
    tenance
    0.79
    entimes
    0.77
     prevail
    0.71
     among
    0.71
     importance
    0.71
     amongst
    0.71
    å§«
    0.70
    SourceFile
    0.68
     belongs
    0.67
    Activations Density 0.008%

    No Known Activations