© 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. 0-RES-JB
    11. 1468
    Prev
    Next
    INDEX
    Explanations

    mentions of the phrase "Unlimited Adventures"

    oai_token-act-pair · gpt-3.5-turbo

    specific environmental organizations and services

    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
     complexion
    -0.69
     meteor
    -0.67
     Dow
    -0.67
     bacterial
    -0.65
    eor
    -0.64
    oxic
    -0.63
     foul
    -0.63
    digit
    -0.61
     glitter
    -0.61
    enes
    -0.61
    POSITIVE LOGITS
     Unlimited
    3.95
     Adventures
    1.12
     Reloaded
    1.04
     Infinity
    1.03
     Trails
    0.99
     Infinite
    0.96
    limited
    0.89
    utsu
    0.83
     Ultra
    0.81
     Unch
    0.80
    Activations Density 0.023%

    No Known Activations