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. 1-RES-JB
    6. 23437
    Prev
    Next
    INDEX
    Explanations

    keywords related to communication, news, and forwarding

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "forward" or "forwarding" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chens
    -0.73
    arcity
    -0.73
    ALE
    -0.73
    avering
    -0.71
    redit
    -0.68
    earable
    -0.68
    gins
    -0.66
    uff
    -0.65
    adle
    -0.64
    ellen
    -0.64
    POSITIVE LOGITS
    forward
    1.34
     forwarding
    1.00
     Forward
    0.98
     forwarded
    0.95
    Forward
    0.94
    £ı
    0.87
    etheless
    0.84
    olicy
    0.80
     forwards
    0.78
    folios
    0.76
    Activations Density 0.010%

    No Known Activations