© 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. 11-RES-JB
    11. 1225
    Prev
    Next
    INDEX
    Explanations

    events or occasions that are happening or being celebrated

    oai_token-act-pair · gpt-3.5-turbo

    references to events, ceremonies, or significant gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unreliable
    -0.78
     porous
    -0.76
     lying
    -0.75
     slippery
    -0.68
     hardened
    -0.68
     fabricated
    -0.67
     resilient
    -0.66
     handwriting
    -0.66
     parasitic
    -0.65
     untreated
    -0.65
    POSITIVE LOGITS
    posium
    1.29
    iversary
    1.28
    Fest
    1.18
    ournament
    1.16
    isode
    1.15
    fest
    1.13
    estival
    1.12
    athlon
    1.08
    ourney
    1.05
     finals
    1.05
    Activations Density 0.287%

    No Known Activations