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

    Neuronpedia

    APICircuit 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. 11750
    Prev
    Next
    INDEX
    Explanations

    references to dreams and fantasies

    oai_token-act-pair · gpt-3.5-turbo

    references to dreams and aspirations

    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
    avis
    -0.80
     LIA
    -0.75
    bidden
    -0.71
    PLA
    -0.69
    nic
    -0.66
    relation
    -0.65
    Correct
    -0.65
     Methodist
    -0.63
    ARI
    -0.63
    FactoryReloaded
    -0.62
    POSITIVE LOGITS
     dreams
    1.37
     dreaming
    1.16
     dream
    1.09
     dreamed
    1.08
    dream
    0.97
     Dreams
    0.89
     fulfilled
    0.84
     imagin
    0.83
     visions
    0.82
     aspirations
    0.80
    Activations Density 0.007%

    No Known Activations