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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18430
    Prev
    Next
    INDEX
    Explanations

    adjectives related to severity or intensity

    oai_token-act-pair · gpt-3.5-turbo

    references to severe or tough situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovember
    -0.92
    phis
    -0.91
    ITNESS
    -0.82
    cellent
    -0.81
    ĸļ
    -0.78
    assies
    -0.75
    ublic
    -0.75
    ICLE
    -0.75
    ividual
    -0.72
    agine
    -0.72
    POSITIVE LOGITS
     harsh
    1.03
    ness
    0.93
     harshly
    0.92
     retribution
    0.88
     punishments
    0.88
     winters
    0.86
    nesses
    0.85
     harsher
    0.85
     punitive
    0.84
    ened
    0.84
    Activations Density 0.025%

    No Known Activations