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. 10666
    Prev
    Next
    INDEX
    Explanations

    phrases related to exciting and positive events or experiences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "exciting" in various contexts

    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
    ©¶æ
    -0.96
    nery
    -0.90
    avis
    -0.74
    bey
    -0.67
    ele
    -0.66
     forgiven
    -0.65
    orders
    -0.65
    ada
    -0.65
    alian
    -0.64
    pel
    -0.63
    POSITIVE LOGITS
    ly
    0.91
    rament
    0.77
     exciting
    0.76
     new
    0.74
     opportunities
    0.73
     Flavoring
    0.72
     developments
    0.72
     possibilities
    0.71
    terday
    0.71
    GGGGGGGG
    0.71
    Activations Density 0.022%

    No Known Activations