© 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. 17666
    Prev
    Next
    INDEX
    Explanations

    instances where the concept of existence is negated or questioned

    oai_token-act-pair · gpt-3.5-turbo

    statements about the concept of existence

    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
    oult
    -0.67
    mar
    -0.67
     ease
    -0.66
    ieu
    -0.65
    jer
    -0.64
    haw
    -0.62
    med
    -0.62
    ajo
    -0.62
    bill
    -0.60
     externalToEVAOnly
    -0.58
    POSITIVE LOGITS
     existed
    0.88
     exists
    0.84
    ãĥ¼ãĥĨãĤ£
    0.82
    nces
    0.78
    rences
    0.77
     exist
    0.75
    entials
    0.75
    entially
    0.73
    ãĥķãĤ©
    0.73
    ĸļ
    0.69
    Activations Density 0.013%

    No Known Activations