© 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. 8-RES-JB
    11. 7896
    Prev
    Next
    INDEX
    Explanations

    words associated with a particular concept, theme, or category

    oai_token-act-pair · gpt-3.5-turbo

    terms that denote associations or connections between concepts

    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
    aneers
    -0.72
    tein
    -0.70
    umblr
    -0.69
    nl
    -0.68
    stall
    -0.68
    AIR
    -0.64
    ettel
    -0.63
    athom
    -0.62
    ²¾
    -0.62
    OUT
    -0.62
    POSITIVE LOGITS
    atively
    0.97
    ively
    0.92
    ativity
    0.91
    ative
    0.81
    atable
    0.73
    eering
    0.72
     affili
    0.71
    ational
    0.69
     associations
    0.69
    hips
    0.69
    Activations Density 0.047%

    No Known Activations