© 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. 4-RES-JB
    11. 6876
    Prev
    Next
    INDEX
    Explanations

    instances where something is being forcefully brought to an end or coming to a striking realization

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate impact or influence

    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
    gio
    -0.77
    uploads
    -0.73
    atts
    -0.71
    idia
    -0.70
    jri
    -0.66
    reviewed
    -0.65
    phrine
    -0.65
    taboola
    -0.64
    urdue
    -0.62
    rss
    -0.62
    POSITIVE LOGITS
    bane
    0.72
     lightning
    0.69
    iron
    0.69
    ritic
    0.68
    road
    0.67
    hare
    0.67
     hardest
    0.66
     itch
    0.66
     stride
    0.64
    ortmund
    0.64
    Activations Density 0.106%

    No Known Activations