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. 20177
    Prev
    Next
    INDEX
    Explanations

    terms related to aging or maturation

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and past participles 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
    kefeller
    -0.77
    Reviewer
    -0.67
    ilater
    -0.66
    iew
    -0.64
    ihar
    -0.64
     sight
    -0.64
     Mub
    -0.63
    issance
    -0.63
     sidel
    -0.62
    isance
    -0.61
    POSITIVE LOGITS
    hog
    1.13
    minster
    0.78
    dit
    0.78
    rets
    0.74
    gers
    0.73
    ged
    0.72
    UGE
    0.72
    lasses
    0.70
    uild
    0.69
    entle
    0.69
    Activations Density 0.026%

    No Known Activations