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. 10914
    Prev
    Next
    INDEX
    Explanations

    words related to information being received or incoming

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "incoming."

    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
    arist
    -0.84
    trak
    -0.77
    ching
    -0.76
     Trance
    -0.76
    arily
    -0.75
    mel
    -0.75
    lance
    -0.74
    agra
    -0.74
    FactoryReloaded
    -0.69
    Dur
    -0.69
    POSITIVE LOGITS
     freshmen
    0.91
     incoming
    0.84
     arrivals
    0.81
     freshman
    0.79
     outgoing
    0.79
    ãģŁ
    0.73
    ãĤĬ
    0.70
     arrival
    0.68
     generation
    0.68
     commissions
    0.68
    Activations Density 0.016%

    No Known Activations