© 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. 10-RES-JB
    11. 758
    Prev
    Next
    INDEX
    Explanations

    terms related to technical features and specifications

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest functionality or convenience in design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rank
    -0.72
    iberal
    -0.69
    clinton
    -0.69
    osterone
    -0.66
     Psychiat
    -0.65
    olan
    -0.65
    xxxx
    -0.64
     Selling
    -0.64
     Pension
    -0.64
     Frie
    -0.64
    POSITIVE LOGITS
     optimum
    1.29
     versatility
    1.29
     flexibility
    1.23
     optimal
    1.21
     smoother
    1.18
     maximum
    1.16
     airflow
    1.15
     seamless
    1.13
     unparalleled
    1.11
     precise
    1.11
    Activations Density 0.245%

    No Known Activations