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. 20494
    Prev
    Next
    INDEX
    Explanations

    studies or research findings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "found" in various contexts

    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
     nom
    -0.62
     Bride
    -0.60
     partic
    -0.60
     concess
    -0.59
    externalActionCode
    -0.59
     gate
    -0.58
     alias
    -0.58
    EStreamFrame
    -0.57
    commit
    -0.57
    via
    -0.57
    POSITIVE LOGITS
    -+-+
    0.76
    oley
    0.74
    oots
    0.71
    itutional
    0.70
    uments
    0.69
    iveness
    0.69
    usky
    0.68
    eele
    0.67
    Leaks
    0.67
    ries
    0.67
    Activations Density 0.050%

    No Known Activations