© 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. 0-RES-JB
    11. 20182
    Prev
    Next
    INDEX
    Explanations

    phrases related to experimentation and medical treatments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to experiments and experimental conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WB
    -0.64
    WB
    -0.61
     videos
    -0.60
     HS
    -0.59
     routers
    -0.59
     Westminster
    -0.58
     Guardians
    -0.57
     video
    -0.57
     AAA
    -0.56
     Athletics
    -0.56
    POSITIVE LOGITS
    iment
    5.03
    iments
    3.77
    imental
    2.91
    imentary
    1.57
    ience
    1.36
    ient
    1.36
    iences
    1.34
    iasm
    1.24
    ienced
    1.15
    ment
    1.13
    Activations Density 0.009%

    No Known Activations