© 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. 7-RES-JB
    11. 12627
    Prev
    Next
    INDEX
    Explanations

    examples where something is linked to something else, such as medical conditions, events, or actions being connected to consequences or causes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate associations or connections between different subjects or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stall
    -0.73
    onew
    -0.69
    annis
    -0.68
    æµ
    -0.66
    /
    -0.64
    DIS
    -0.64
    sburg
    -0.61
    ifter
    -0.59
     outnumbered
    -0.59
    kay
    -0.59
    POSITIVE LOGITS
     thereto
    0.77
     knot
    0.77
    edin
    0.77
    linked
    0.77
     closely
    0.76
     dots
    0.69
     disparate
    0.69
     statically
    0.68
    axter
    0.66
     geographically
    0.66
    Activations Density 0.046%

    No Known Activations