© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 15052
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety and security

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to safety and legality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sbm
    -0.85
    okemon
    -0.81
     Cosponsors
    -0.75
    tera
    -0.74
    qt
    -0.73
    cules
    -0.70
     Bengals
    -0.67
    çīĪ
    -0.65
    mere
    -0.65
    hoe
    -0.64
    POSITIVE LOGITS
     efficient
    1.16
     nutritious
    1.12
     orderly
    1.08
     usable
    1.08
     affordable
    1.07
     sustainable
    1.07
     reliable
    1.07
     equitable
    1.03
     stable
    1.02
     durable
    1.02
    Activations Density 0.170%

    No Known Activations