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. 11-RES-JB
    6. 8533
    Prev
    Next
    INDEX
    Explanations

    phrases related to business transactions in various industries, including mentions of specific countries and products

    oai_token-act-pair · gpt-3.5-turbo

    information related to significant health impacts or risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Decision
    -0.62
     UNHCR
    -0.59
    insk
    -0.57
     everybody
    -0.55
    BUS
    -0.54
     Tournament
    -0.52
     organis
    -0.51
    Fine
    -0.51
    markets
    -0.51
     ï
    -0.51
    POSITIVE LOGITS
     similarly
    0.88
     equivalents
    0.87
     similar
    0.81
     versions
    0.80
    paralle
    0.77
     emulate
    0.75
     utilizing
    0.74
    odied
    0.74
    icient
    0.70
    earable
    0.70
    Activations Density 1.062%

    No Known Activations