© 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. 3431
    Prev
    Next
    INDEX
    Explanations

    numerical values preceded by a dollar sign

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and years associated with various data points

    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
     bleach
    -0.75
    istical
    -0.73
    onite
    -0.72
    iated
    -0.71
    ioned
    -0.70
    ications
    -0.69
    ist
    -0.67
    icals
    -0.65
    iations
    -0.64
    ovie
    -0.64
    POSITIVE LOGITS
    08
    1.16
    09
    1.16
    06
    1.11
    07
    1.11
    05
    1.10
    04
    1.05
    090
    1.03
    03
    1.02
    088
    1.01
    089
    1.00
    Activations Density 0.124%

    No Known Activations