© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 14136
    Prev
    Next
    INDEX
    Explanations

    references related to statistical data and percentages

    oai_token-act-pair · gpt-3.5-turbo

    information related to statistics and percentages

    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
     extraord
    -0.67
    èª
    -0.65
     indef
    -0.64
    ï¸
    -0.60
    hement
    -0.59
     Puzz
    -0.59
     beck
    -0.58
    assetsadobe
    -0.58
    aciously
    -0.58
     kindly
    -0.58
    POSITIVE LOGITS
     surveyed
    1.21
     population
    1.09
     polled
    1.06
     respondents
    1.00
     workforce
    0.99
     GDP
    0.91
     households
    0.91
     total
    0.91
     populace
    0.85
     fatalities
    0.82
    Activations Density 0.329%

    No Known Activations