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. 9770
    Prev
    Next
    INDEX
    Explanations

    terms related to catastrophic events or breakdowns

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "collapse" and its various forms

    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
    qua
    -0.80
    friends
    -0.77
    ju
    -0.72
    lean
    -0.70
    ledge
    -0.69
    Choice
    -0.69
    cil
    -0.69
    prim
    -0.69
    etch
    -0.69
    ña
    -0.68
    POSITIVE LOGITS
     inertia
    0.82
    ateral
    0.80
     containment
    0.79
    ulence
    0.79
     collapse
    0.79
    opian
    0.78
    ibility
    0.77
     contag
    0.76
    icter
    0.73
     tremend
    0.73
    Activations Density 0.030%

    No Known Activations