© 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. 10356
    Prev
    Next
    INDEX
    Explanations

    phrases related to advising or recommending actions

    oai_token-act-pair · gpt-3.5-turbo

    calls to action or requests for people to take specific actions

    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
     Landing
    -0.65
    mill
    -0.63
    Guard
    -0.62
    eworks
    -0.62
     owned
    -0.59
     tun
    -0.59
     Accounting
    -0.59
     Laure
    -0.57
     Composite
    -0.57
    boarding
    -0.57
    POSITIVE LOGITS
     urge
    3.93
     urges
    2.50
     temptation
    1.68
     impulse
    1.50
     compulsion
    1.43
     encourage
    1.38
     urging
    1.37
     advise
    1.35
     inclination
    1.33
     urged
    1.31
    Activations Density 0.011%

    No Known Activations