© 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. 4-RES-JB
    11. 14465
    Prev
    Next
    INDEX
    Explanations

    keywords related to technology, including cybersecurity and medical technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to safety, security, and health issues

    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
    hap
    -0.69
    atom
    -0.64
     Jah
    -0.62
    OOOO
    -0.59
    JB
    -0.59
    nen
    -0.58
    xon
    -0.58
    _-_
    -0.57
    aird
    -0.57
     Jeep
    -0.57
    POSITIVE LOGITS
     emergencies
    0.72
     stimuli
    0.71
     pointers
    0.67
     interventions
    0.66
     initiation
    0.66
     terminology
    0.66
     etiquette
    0.66
     aggregation
    0.66
     practition
    0.65
     havens
    0.65
    Activations Density 0.730%

    No Known Activations