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. 18186
    Prev
    Next
    INDEX
    Explanations

    dates and locations related to product releases

    oai_token-act-pair · gpt-3.5-turbo

    specific details regarding the release dates and platforms of gaming content

    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
    entimes
    -0.69
     probing
    -0.69
     volunteered
    -0.68
    yll
    -0.68
    adier
    -0.66
    paio
    -0.65
    vec
    -0.65
    ullivan
    -0.65
    idious
    -0.65
    paren
    -0.64
    POSITIVE LOGITS
     TBA
    1.00
    iversary
    0.90
     2019
    0.89
     NX
    0.86
     Playstation
    0.86
    ember
    0.84
     TBD
    0.84
     Ubisoft
    0.83
     onwards
    0.81
     Deadline
    0.81
    Activations Density 0.473%

    No Known Activations