© 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. 2-RES-JB
    11. 733
    Prev
    Next
    INDEX
    Explanations

    the word "curious"

    oai_token-act-pair · gpt-4-turbo

    phrases related to curiosity and inquisitiveness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "curious" and its variations in different contexts

    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
    adier
    -0.75
     Depot
    -0.65
    atra
    -0.64
    ACP
    -0.64
    ©¶æ
    -0.63
     preached
    -0.63
    ohm
    -0.62
    accept
    -0.62
    ffen
    -0.61
    astered
    -0.61
    POSITIVE LOGITS
     curiosity
    1.10
     curious
    1.00
     onlook
    0.87
    iously
    0.87
     Curious
    0.86
     passers
    0.82
     probing
    0.80
    ioned
    0.77
    Magikarp
    0.75
    ively
    0.73
    Activations Density 0.009%

    No Known Activations