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. 11407
    Prev
    Next
    INDEX
    Explanations

    instances of text related to software updates, project announcements, and interactions with users

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the pronouns "we" and "our," indicating a focus on collective action or community involvement

    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
     starvation
    -0.61
    Appearances
    -0.59
     Eleven
    -0.59
     malnutrition
    -0.58
     blindness
    -0.57
     totality
    -0.57
     Congressional
    -0.57
     AIDS
    -0.56
     Crimes
    -0.56
     LSD
    -0.55
    POSITIVE LOGITS
    've
    1.21
    'll
    1.06
    're
    1.06
    bsite
    1.02
    athered
    1.00
     intend
    0.96
     anticipate
    0.94
    'd
    0.94
     recommend
    0.94
     strive
    0.93
    Activations Density 0.253%

    No Known Activations