© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 10097
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Apothercarium"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Ap" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stal
    -0.74
    itaire
    -0.72
    illet
    -0.70
    \\\\\\\\\\\\\\\\
    -0.67
     disadvant
    -0.67
    RW
    -0.67
    kered
    -0.66
     puck
    -0.65
    CHQ
    -0.64
    inders
    -0.63
    POSITIVE LOGITS
     Ap
    3.77
    Ap
    2.61
     ap
    1.87
     Asc
    1.22
     Apocalypse
    1.20
    ap
    1.19
     Kap
    1.16
     Aph
    1.15
     apes
    1.14
    apo
    1.13
    Activations Density 0.011%

    No Known Activations