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. 6-RES-JB
    6. 20193
    Prev
    Next
    INDEX
    Explanations

    economic and statistical information specific to reports and studies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to statistical data and reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icably
    -0.75
    agically
    -0.73
    fit
    -0.71
    ²¾
    -0.71
    quit
    -0.68
    terior
    -0.68
    ctor
    -0.67
    ifles
    -0.67
    tone
    -0.67
    ivas
    -0.66
    POSITIVE LOGITS
     OECD
    0.89
     Compass
    0.88
     Nielsen
    0.85
     Kant
    0.81
     Wallet
    0.80
     Moody
    0.79
     Fried
    0.76
     comparison
    0.75
    manac
    0.73
     Statistics
    0.72
    Activations Density 0.157%

    No Known Activations