© 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. 2-RES-JB
    11. 17573
    Prev
    Next
    INDEX
    Explanations

    phrases related to exploration and investigation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "explore" and its variations, indicating a focus on investigation or discovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fixed
    -0.80
    die
    -0.80
    death
    -0.75
    jud
    -0.72
    absolute
    -0.69
    wa
    -0.68
    cake
    -0.68
    venge
    -0.67
    lat
    -0.67
    eat
    -0.67
    POSITIVE LOGITS
    ĸļ
    0.96
     Explore
    0.94
    çīĪ
    0.87
     exploring
    0.84
     IPM
    0.79
     exploration
    0.77
    issance
    0.77
    izabeth
    0.76
    emouth
    0.74
    ibility
    0.72
    Activations Density 0.015%

    No Known Activations