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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 19860
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Sydney" at different importance levels

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Sydney" and variants of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perfect
    -0.73
     caution
    -0.72
     resolve
    -0.70
    perture
    -0.67
    OPER
    -0.61
     confidence
    -0.60
     clar
    -0.60
    complete
    -0.59
    IME
    -0.59
    cean
    -0.59
    POSITIVE LOGITS
    yd
    1.21
    aniel
    0.94
    elta
    0.92
    ynamic
    0.92
    roxy
    0.89
    rox
    0.88
    zx
    0.86
    ield
    0.85
    orks
    0.84
    ritch
    0.83
    Activations Density 0.009%

    No Known Activations