© 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. 11352
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to the act of invoking or calling upon something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "invoke" and its variations

    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
     flats
    -0.82
    Rated
    -0.72
     Trends
    -0.67
     pod
    -0.66
    edin
    -0.66
     Nico
    -0.65
    NY
    -0.65
    road
    -0.64
     plastic
    -0.63
    Quality
    -0.63
    POSITIVE LOGITS
     invoked
    3.17
     invoke
    3.05
     invoking
    2.86
     invocation
    2.74
     evoke
    1.50
    invoke
    1.42
     recite
    1.13
     summoning
    1.10
     inv
    1.07
    Inv
    1.01
    Activations Density 0.016%

    No Known Activations