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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 22863
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing desires or hopes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "wish" and its variations

    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
    agonists
    -0.73
    helle
    -0.71
    orously
    -0.70
    tics
    -0.67
    itu
    -0.66
    models
    -0.64
    iltr
    -0.64
    entin
    -0.63
    é¾
    -0.63
    nih
    -0.63
    POSITIVE LOGITS
     wishes
    1.04
     aloud
    0.88
    bone
    0.87
     fulfil
    0.84
     wish
    0.82
    bones
    0.78
    reprene
    0.78
     wished
    0.77
    irection
    0.77
     reper
    0.76
    Activations Density 0.024%

    No Known Activations