© 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. 4-RES-JB
    6. 4351
    Prev
    Next
    INDEX
    Explanations

    legal and contractual terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to agreements and legal conditions

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

    No Comments

    Negative Logits
    ï¸ı
    -0.98
    Screenshot
    -0.81
    PDF
    -0.78
    Brain
    -0.77
    Around
    -0.76
    nir
    -0.74
    exper
    -0.73
    ppa
    -0.73
    pause
    -0.73
     Canaver
    -0.73
    POSITIVE LOGITS
     lawfully
    1.17
     practicable
    1.10
     specified
    1.08
     lawful
    1.06
     pursuant
    1.04
     applicable
    1.04
     prescribed
    1.02
     incidental
    1.02
     persons
    1.00
     ineligible
    0.98
    Activations Density 0.952%

    No Known Activations