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. 10-RES-JB
    6. 9437
    Prev
    Next
    INDEX
    Explanations

    concepts related to societal change and development

    oai_token-act-pair · gpt-3.5-turbo

    references to changes or advancements in societal or technological eras

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    charges
    -0.95
    ributes
    -0.92
    sever
    -0.88
     pts
    -0.79
    osponsors
    -0.76
    issues
    -0.75
     actionGroup
    -0.74
     referrals
    -0.73
     counts
    -0.73
    marks
    -0.72
    POSITIVE LOGITS
     world
    1.41
     society
    1.41
     universe
    1.40
     era
    1.40
     dystop
    1.38
     paradise
    1.36
     civilisation
    1.34
     civilization
    1.34
     cosmos
    1.28
     paradigm
    1.26
    Activations Density 0.354%

    No Known Activations