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. 7-RES-JB
    6. 998
    Prev
    Next
    INDEX
    Explanations

    words related to negative emotions or qualities such as "awful," "horrible," and "terrible."

    oai_token-act-pair · gpt-3.5-turbo

    terms expressing negative evaluations or descriptions of experiences, conditions, or entities

    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
    ership
    -0.87
    pai
    -0.86
    irs
    -0.82
    ilus
    -0.77
    idable
    -0.76
    essor
    -0.74
    eters
    -0.72
    andr
    -0.71
    restricted
    -0.71
    olate
    -0.70
    POSITIVE LOGITS
     smelling
    0.85
     sounding
    0.83
     nightmares
    0.82
     nightmare
    0.80
     tasting
    0.78
     horrible
    0.76
     manners
    0.75
     headache
    0.74
     ordeal
    0.74
     blow
    0.73
    Activations Density 0.035%

    No Known Activations