© 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. 10-RES-JB
    11. 4627
    Prev
    Next
    INDEX
    Explanations

    phrases signaling the need for action or a change in direction

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "time to" indicating a call for action or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    secret
    -0.70
    similar
    -0.68
    ELD
    -0.67
    hent
    -0.66
    Ess
    -0.65
    furt
    -0.64
    soever
    -0.63
    una
    -0.63
    existent
    -0.63
    ¿½
    -0.62
    POSITIVE LOGITS
     revisit
    1.38
     rethink
    1.32
     rejoice
    1.24
     reconsider
    1.24
     retire
    1.22
     celebrate
    1.12
     ditch
    1.02
     remind
    1.01
     introduce
    1.00
     buckle
    0.99
    Activations Density 0.105%

    No Known Activations