© 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. 1311
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific events or meetings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of events and attendance-related information

    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
     hardness
    -0.77
     flawed
    -0.71
     poisons
    -0.70
    opathy
    -0.69
     Weak
    -0.69
     harmful
    -0.69
     psychopath
    -0.68
     nihil
    -0.67
    terness
    -0.65
    icide
    -0.65
    POSITIVE LOGITS
    Tickets
    1.15
     attendance
    1.01
     hosting
    0.99
    noon
    0.99
     tours
    0.98
     pilgrimage
    0.97
     visit
    0.97
     venue
    0.97
     Pavilion
    0.96
     guests
    0.93
    Activations Density 1.449%

    No Known Activations