© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 20344
    Prev
    Next
    INDEX
    Explanations

    phrases related to rules or instructions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "guidelines" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    some
    -0.73
    joy
    -0.68
    tal
    -0.68
     Roses
    -0.66
    jiang
    -0.66
    Leary
    -0.66
    joice
    -0.64
    parts
    -0.63
    rama
    -0.63
    false
    -0.63
    POSITIVE LOGITS
     guidelines
    1.22
    idelines
    1.09
    DragonMagazine
    1.07
     guideline
    1.01
     governing
    0.95
     Guidelines
    0.91
     rules
    0.82
     dictates
    0.82
     directives
    0.79
     dictate
    0.76
    Activations Density 0.013%

    No Known Activations