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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 3736
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases indicating a desire or intention to take a specific action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express desires or intentions to perform actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.71
    banks
    -0.70
    grounds
    -0.70
    quickShipAvailable
    -0.70
    front
    -0.68
    wikipedia
    -0.67
    ãĥ³ãĤ¸
    -0.66
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.64
    written
    -0.64
    iously
    -0.64
    POSITIVE LOGITS
     browse
    1.02
     keep
    0.98
     maximize
    0.94
     download
    0.94
     qualify
    0.93
     subscribe
    0.93
     give
    0.91
     ride
    0.90
     make
    0.89
     indulge
    0.89
    Activations Density 0.115%

    No Known Activations