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. 14219
    Prev
    Next
    INDEX
    Explanations

    URLs mentioning specific locations

    oai_token-act-pair · gpt-3.5-turbo

    web-related URLs and coding elements

    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
    ilda
    -0.65
    shire
    -0.62
     ACTIONS
    -0.62
    tein
    -0.60
     Skinner
    -0.58
    ishers
    -0.56
    AFTA
    -0.56
    ESA
    -0.55
    enment
    -0.54
    heit
    -0.53
    POSITIVE LOGITS
    soDeliveryDate
    0.60
    eper
    0.60
    ï¸ı
    0.60
    Writer
    0.59
     Unloaded
    0.58
    Lens
    0.58
    itars
    0.56
    unic
    0.55
    Plex
    0.55
    processing
    0.53
    Activations Density 1.240%

    No Known Activations