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. 1468
    Prev
    Next
    INDEX
    Explanations

    phrases related to "Jack the Ripper."

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the word "ipper," indicating a focus on characters or entities related to that term

    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
    ¿½
    -0.95
    ADRA
    -0.87
    rade
    -0.73
    ãĤ£
    -0.70
    places
    -0.69
     Yel
    -0.69
    cn
    -0.69
    hemat
    -0.67
    ©¶æ
    -0.65
    ³
    -0.65
    POSITIVE LOGITS
    ipper
    0.97
    iness
    0.90
    clips
    0.90
    ily
    0.87
    maid
    0.84
    chief
    0.80
    jack
    0.71
    olean
    0.71
    llan
    0.69
    aired
    0.69
    Activations Density 0.023%

    No Known Activations