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. 3251
    Prev
    Next
    INDEX
    Explanations

    words related to aspirations, desires, and ambitions

    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 @ 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
    avis
    -0.80
    idges
    -0.70
    oute
    -0.69
    andise
    -0.67
    ãĥĺãĥ©
    -0.67
     ease
    -0.66
     wrinkles
    -0.65
    anti
    -0.64
    ahon
    -0.64
     tabl
    -0.64
    POSITIVE LOGITS
    tek
    0.98
    scape
    0.95
     dreaming
    0.91
     dream
    0.87
    dream
    0.85
     dreams
    0.84
    liner
    0.79
    Hack
    0.77
    Dream
    0.77
    hack
    0.76
    Activations Density 0.019%

    No Known Activations