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. 18724
    Prev
    Next
    INDEX
    Explanations

    digital object identifiers (DOIs)

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and specific identifiers such as DOI references

    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
    Dash
    -0.82
    estones
    -0.74
     Torch
    -0.69
     torches
    -0.67
    estone
    -0.67
    ouses
    -0.65
     blat
    -0.65
    ulia
    -0.65
    ttle
    -0.64
    hello
    -0.63
    POSITIVE LOGITS
     DOI
    0.89
    doi
    0.88
     PubMed
    0.87
    1016
    0.83
    ournals
    0.82
     doi
    0.80
     Medline
    0.76
     suppl
    0.73
     ISI
    0.71
     Crossref
    0.69
    Activations Density 0.069%

    No Known Activations