© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 4087
    Prev
    Next
    INDEX
    Explanations

    references to a specific television show called "Survivor."

    oai_token-act-pair · gpt-3.5-turbo

    references to the reality show "Survivor."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gar
    -0.79
     Erd
    -0.78
    enez
    -0.74
     fres
    -0.71
     deliveries
    -0.69
     fortunes
    -0.69
     od
    -0.69
    ioch
    -0.68
     olig
    -0.67
    hai
    -0.67
    POSITIVE LOGITS
     Survivor
    3.76
    Surv
    3.27
     Surviv
    2.09
     Tribal
    1.94
    surv
    1.87
     Survivors
    1.79
     SUR
    1.49
     Survival
    1.47
     Surv
    1.44
     Summoner
    1.33
    Activations Density 0.037%

    No Known Activations