Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 4467
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the word "ultimatum" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to specific ultimatums and ketogenic concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.74
    stocks
    -0.74
    ãģĦ
    -0.74
    士
    -0.69
    ño
    -0.69
    ãģ¦
    -0.69
    REDACTED
    -0.68
    phone
    -0.66
    ppo
    -0.66
    ãģĨ
    -0.65
    POSITIVE LOGITS
    imates
    1.45
    raviolet
    1.31
    hetically
    0.98
    reme
    0.97
    imately
    0.97
    rap
    0.95
    rav
    0.95
    ypes
    0.94
    eenth
    0.93
    ritional
    0.93
    Activations Density 0.026%

    No Known Activations