Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 19547
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to invoking or calling upon something for a specific purpose

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "invoke" and its variations in the context of citing or referring to concepts or authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ±
    -0.76
     Flo
    -0.75
    indust
    -0.74
    cas
    -0.73
    ¼
    -0.71
    ¯
    -0.70
    shop
    -0.67
     Freddie
    -0.66
     Aden
    -0.66
    ¸
    -0.66
    POSITIVE LOGITS
     invoke
    1.31
     invoking
    1.20
     invoked
    1.16
     invocation
    0.98
     evoke
    0.85
    ulnerable
    0.84
    ierrez
    0.83
    ansas
    0.80
    eers
    0.79
    asions
    0.78
    Activations Density 0.013%

    No Known Activations