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. 6630
    Prev
    Next
    INDEX
    Explanations

    comparisons or contrasts being made between different entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    comparisons or contrasts between different subjects

    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
     parliament
    -0.75
    WOOD
    -0.70
    ario
    -0.66
    RM
    -0.65
    ATA
    -0.63
     Parliament
    -0.62
    ktop
    -0.60
    ornia
    -0.60
    igning
    -0.59
    redo
    -0.58
    POSITIVE LOGITS
    MpServer
    0.95
     favorably
    0.86
    ãĤ§
    0.78
    etheus
    0.77
     dots
    0.76
    Ö¼
    0.71
    imilar
    0.70
     CLSID
    0.69
    rimp
    0.68
    apse
    0.67
    Activations Density 0.184%

    No Known Activations