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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 7823
    Prev
    Next
    INDEX
    Explanations

    phrases related to good luck and well-wishing

    oai_token-act-pair · gpt-3.5-turbo

    expressions of good luck or well-wishing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anyon
    -0.69
    cious
    -0.67
    vez
    -0.66
    deen
    -0.66
    apeake
    -0.64
    cept
    -0.63
    aration
    -0.61
    het
    -0.61
    avez
    -0.61
    nants
    -0.61
    POSITIVE LOGITS
     charms
    1.12
     charm
    0.90
    iest
    0.84
    istically
    0.79
    ily
    0.78
    nings
    0.76
     dice
    0.76
    finding
    0.74
     finding
    0.69
     Carbuncle
    0.69
    Activations Density 0.027%

    No Known Activations