© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 363
    Prev
    Next
    INDEX
    Explanations

    phrases related to disappearance or vanishing

    oai_token-act-pair · gpt-3.5-turbo

    words indicating the act of disappearing or vanishing

    oai_token-act-pair · gpt-4-turbo

    terms related to disappearance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stra
    -0.63
    gp
    -0.63
    gard
    -0.63
    appropriate
    -0.62
    wyn
    -0.61
    Stra
    -0.61
    wave
    -0.61
    mk
    -0.60
    vP
    -0.60
    ube
    -0.60
    POSITIVE LOGITS
     disappear
    1.23
     disappeared
    1.07
     vanish
    1.04
     mysteriously
    0.96
     disappears
    0.95
     disappearance
    0.95
     vanished
    0.94
     disappearing
    0.87
     vanishing
    0.87
     extinct
    0.84
    Activations Density 0.013%

    No Known Activations