© 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. 4-RES-JB
    11. 2838
    Prev
    Next
    INDEX
    Explanations

    phrases related to exploration and adventure

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "explore" in various contexts

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

    No Comments

    Negative Logits
    fight
    -0.71
    fixed
    -0.70
    jud
    -0.67
    ivari
    -0.66
    enta
    -0.66
    lat
    -0.62
    corn
    -0.62
    wa
    -0.62
    ĪĴ
    -0.61
    die
    -0.61
    POSITIVE LOGITS
    ĸļ
    0.95
    ibility
    0.85
    vier
    0.84
    ibilities
    0.83
    ationally
    0.80
     Explore
    0.79
    prising
    0.79
    Ô
    0.78
    çīĪ
    0.76
    ONSORED
    0.74
    Activations Density 0.023%

    No Known Activations