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

    Neuronpedia

    Jacobian LensNEW
    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. 12617
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a need or necessity for something to be done or in place

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express necessity or requirements for various actions or conditions

    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
    thal
    -0.64
    aughed
    -0.61
     Happy
    -0.57
     calm
    -0.57
    atern
    -0.57
     laughing
    -0.56
    oman
    -0.55
    laugh
    -0.54
     fault
    -0.54
     warm
    -0.53
    POSITIVE LOGITS
     requires
    3.28
    requires
    2.54
     require
    2.30
     involves
    2.06
     entails
    2.01
     relies
    1.98
     Requires
    1.89
     depends
    1.83
     prohibits
    1.79
     forbids
    1.74
    Activations Density 0.019%

    No Known Activations