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. 4720
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to harshness or severity in context

    oai_token-act-pair · gpt-3.5-turbo

    the word "harsh" and its variations related to difficult or severe conditions

    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
    phis
    -0.93
    ovember
    -0.89
    cellent
    -0.87
    ĸļ
    -0.84
    assies
    -0.82
    ICLE
    -0.77
    ividual
    -0.77
    ablish
    -0.75
    duct
    -0.74
    xxxxxxxx
    -0.73
    POSITIVE LOGITS
     harsh
    1.06
    ness
    1.03
    nesses
    0.94
     winters
    0.94
     harshly
    0.93
     punishments
    0.92
     retribution
    0.91
     punishment
    0.88
     harsher
    0.87
     hars
    0.86
    Activations Density 0.028%

    No Known Activations