© 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. 6-RES-JB
    11. 2988
    Prev
    Next
    INDEX
    Explanations

    keywords related to technical instructions or steps

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to technology, specifically printing and programming outputs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ethics
    -0.75
     preempt
    -0.72
     stake
    -0.71
     upbringing
    -0.71
     contem
    -0.69
     legisl
    -0.69
     derog
    -0.69
    istani
    -0.68
     educ
    -0.68
     economics
    -0.67
    POSITIVE LOGITS
     indistinguishable
    0.92
     resembling
    0.89
     noticeable
    0.85
    ptoms
    0.81
     streaks
    0.77
     noticeably
    0.77
     shimmer
    0.76
    luster
    0.75
    ifferent
    0.75
     usable
    0.74
    Activations Density 0.840%

    No Known Activations