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. 0-RES-JB
    6. 19814
    Prev
    Next
    INDEX
    Explanations

    references to aspirations or ambitions

    oai_token-act-pair · gpt-3.5-turbo

    references to "dream" and related concepts of aspiration or ambition

    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
    istrates
    -0.75
    []
    -0.74
    SPONSORED
    -0.72
     Correction
    -0.70
    available
    -0.69
     Removed
    -0.67
     Bearing
    -0.66
     Factors
    -0.65
    votes
    -0.64
    encing
    -0.64
    POSITIVE LOGITS
     dream
    3.91
     dreams
    2.90
    dream
    2.45
     dreamed
    2.32
     dreaming
    2.28
     Dream
    2.20
    Dream
    2.15
     nightmare
    1.93
     Dreams
    1.86
     nightmares
    1.66
    Activations Density 0.022%

    No Known Activations