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. 8-RES-JB
    6. 23038
    Prev
    Next
    INDEX
    Explanations

    financial figures and statistics

    oai_token-act-pair · gpt-3.5-turbo

    numeric data and statistics related to financial or health-related expenditures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odox
    -0.81
    optional
    -0.74
    sonian
    -0.69
     horm
    -0.69
     deterior
    -0.67
     dogma
    -0.67
     someday
    -0.66
     improv
    -0.65
    }}}
    -0.65
     proverb
    -0.65
    POSITIVE LOGITS
     total
    1.07
     totaled
    0.99
     totaling
    0.95
     totals
    0.92
    Total
    0.90
     tallied
    0.90
     337
    0.90
     registrations
    0.90
    total
    0.89
     283
    0.89
    Activations Density 1.011%

    No Known Activations