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. 8-RES-JB
    6. 8752
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and phrases referring to or involving people

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \\\\\\\\
    -0.76
    rection
    -0.62
    Poké
    -0.56
    roo
    -0.56
    potion
    -0.55
     Advertisement
    -0.55
     clarification
    -0.55
    rontal
    -0.55
     sqor
    -0.55
    alin
    -0.55
    POSITIVE LOGITS
     composing
    1.08
     closest
    1.05
     involved
    1.01
     nearest
    1.00
     responsible
    0.91
     surrounding
    0.91
    folk
    0.89
     surveyed
    0.87
     entrusted
    0.86
    responsible
    0.82
    Activations Density 0.298%

    No Known Activations