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. 21311
    Prev
    Next
    INDEX
    Explanations

    mentions of high-stress situations, conflicts, and challenges

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to social and political movements

    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
    aka
    -0.62
    arta
    -0.61
     hangs
    -0.60
    onga
    -0.59
     Allaah
    -0.58
     awa
    -0.58
    onto
    -0.57
    osa
    -0.57
    anges
    -0.56
     Sketch
    -0.56
    POSITIVE LOGITS
     Ples
    0.65
     last
    0.65
     enthusi
    0.64
     outcry
    0.63
     yesterday
    0.62
     initially
    0.61
     applause
    0.59
     pandemonium
    0.59
     uproar
    0.59
     Thiel
    0.58
    Activations Density 1.855%

    No Known Activations