© 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. 0-RES-JB
    11. 4777
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Ava"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ava" in various contexts

    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
     transcription
    -0.68
     crank
    -0.67
     ballpark
    -0.65
     penny
    -0.63
     chars
    -0.63
     print
    -0.63
     prep
    -0.62
     tune
    -0.61
     character
    -0.60
     COP
    -0.60
    POSITIVE LOGITS
    ava
    4.54
    av
    1.36
    avi
    1.33
    avia
    1.20
    aves
    1.17
    avan
    1.17
    ova
    1.09
    avorite
    1.03
    aval
    1.03
    uca
    1.03
    Activations Density 0.007%

    No Known Activations