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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 22285
    Prev
    Next
    INDEX
    Explanations

    words related to emergencies or urgent situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "emergency" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pilgrim
    -0.69
     Ogre
    -0.67
     Strauss
    -0.65
     Machines
    -0.65
    »Ĵ
    -0.64
     guiActiveUnfocused
    -0.63
     Yoga
    -0.60
     Shades
    -0.60
     hanging
    -0.59
     cooker
    -0.58
    POSITIVE LOGITS
    gency
    1.27
    gent
    1.19
    gencies
    1.12
    itus
    1.08
    oing
    0.94
    gence
    0.94
    acy
    0.94
    idian
    0.92
    andum
    0.89
    rence
    0.87
    Activations Density 0.023%

    No Known Activations