© 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. 11487
    Prev
    Next
    INDEX
    Explanations

    phrases related to making adjustments or modifications without significant impact or interference

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions or processes that can occur without additional requirements or complications

    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
    raq
    -0.96
    geist
    -0.82
    late
    -0.75
    oled
    -0.73
    mun
    -0.71
    aez
    -0.70
     Facts
    -0.70
    soon
    -0.70
    lator
    -0.70
    ounce
    -0.69
    POSITIVE LOGITS
     risking
    1.39
     sacrificing
    1.37
     harming
    1.30
     compromising
    1.30
     needing
    1.25
     worrying
    1.21
     interruption
    1.15
     relying
    1.15
     bothering
    1.14
     disrupting
    1.12
    Activations Density 0.049%

    No Known Activations