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. 1-RES-JB
    6. 7813
    Prev
    Next
    INDEX
    Explanations

    adjectives describing something negatively

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "terrible" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pai
    -0.99
    ership
    -0.92
    illary
    -0.84
    cript
    -0.82
    ilus
    -0.82
    adr
    -0.81
    illance
    -0.81
    paio
    -0.80
    ipel
    -0.80
    sterdam
    -0.80
    POSITIVE LOGITS
     earthqu
    1.03
     awful
    0.99
     terrible
    0.97
     horrible
    0.94
     nightmare
    0.94
     nightmares
    0.93
     conflic
    0.92
     havoc
    0.89
     headache
    0.87
     dreadful
    0.82
    Activations Density 0.010%

    No Known Activations