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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1030
    Prev
    Next
    INDEX
    Explanations

    terms related to "levo" or "lev-" prefixes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lev" in various contexts

    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
    TERN
    -0.75
    SEE
    -0.74
    natureconservancy
    -0.72
    ãģ¦
    -0.69
     Forth
    -0.68
    luaj
    -0.64
     WS
    -0.63
    giving
    -0.62
    Accessory
    -0.62
     Catalyst
    -0.61
    POSITIVE LOGITS
    isions
    1.13
    lev
    1.10
    ision
    1.05
    itating
    1.03
    ices
    0.93
    iating
    0.91
    ideos
    0.90
    ault
    0.89
    iev
    0.89
    igon
    0.86
    Activations Density 0.006%

    No Known Activations