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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 16122
    Prev
    Next
    INDEX
    Explanations

    years mentioned in specific contexts

    oai_token-act-pair · gpt-3.5-turbo

    specific years and significant events associated with those years

    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
    acci
    -0.73
     maple
    -0.62
     Manufacturer
    -0.62
    abilia
    -0.59
    icone
    -0.59
     diaper
    -0.57
     Sins
    -0.57
     bip
    -0.57
     baking
    -0.57
     tire
    -0.56
    POSITIVE LOGITS
    AMY
    0.73
     Nicol
    0.73
     developments
    0.71
    GV
    0.71
     Edu
    0.68
    IVERS
    0.67
    BILL
    0.64
    UTERS
    0.64
     Gins
    0.64
    Guard
    0.63
    Activations Density 0.243%

    No Known Activations