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. 11728
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscribing to newsletters

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to subscribing to newsletters and confirmation messages

    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
    mas
    -0.77
    imm
    -0.72
    gru
    -0.69
    dies
    -0.68
    saf
    -0.67
    tains
    -0.65
    omorphic
    -0.64
     Alps
    -0.64
     Clown
    -0.63
    arth
    -0.61
    POSITIVE LOGITS
     Cancel
    0.83
     antioxid
    0.77
    ONSORED
    0.72
    cknow
    0.64
     URL
    0.63
    entimes
    0.62
     Search
    0.62
    Sync
    0.62
     Journals
    0.62
    Subscribe
    0.62
    Activations Density 0.149%

    No Known Activations