Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 3292
    Prev
    Next
    INDEX
    Explanations

    the word "Peach" associated with numerical values

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Peach" and related terms or names

    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
    enegger
    -0.72
    enance
    -0.68
    orage
    -0.67
     Kazakh
    -0.66
    ãĥĩ
    -0.65
    inav
    -0.64
    binding
    -0.63
    schild
    -0.61
     Monarch
    -0.61
     nucleus
    -0.61
    POSITIVE LOGITS
    oples
    1.09
    omore
    0.95
    ggy
    0.92
    Pe
    0.88
    ppa
    0.86
    zee
    0.84
    aky
    0.83
    cies
    0.81
    anut
    0.80
    lihood
    0.80
    Activations Density 0.012%

    No Known Activations