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. 20425
    Prev
    Next
    INDEX
    Explanations

    verbs related to disappearance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to disappearance or vanishing

    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
    stra
    -0.64
    annis
    -0.61
    vironments
    -0.61
    axter
    -0.60
    creation
    -0.60
    leading
    -0.60
    weeney
    -0.59
    wyn
    -0.58
    rikes
    -0.58
    verbs
    -0.58
    POSITIVE LOGITS
     mysteriously
    0.91
     disappear
    0.88
     vanish
    0.78
     Jagu
    0.78
     disappearance
    0.76
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.74
     unnoticed
    0.72
     disappears
    0.72
     disappeared
    0.71
    orph
    0.71
    Activations Density 0.019%

    No Known Activations