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. 15477
    Prev
    Next
    INDEX
    Explanations

    terms related to societal issues and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    phrases with high-frequency conjunctions and the word "and."

    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
    IRE
    -0.72
    etting
    -0.64
    united
    -0.58
    arov
    -0.56
    fold
    -0.54
    GO
    -0.54
    OGR
    -0.54
    rison
    -0.54
    HEAD
    -0.53
    REE
    -0.53
    POSITIVE LOGITS
     the
    1.03
    the
    0.93
     });
    0.67
     Cth
    0.67
     its
    0.67
     THE
    0.66
     those
    0.65
    ata
    0.65
     whoever
    0.62
     The
    0.62
    Activations Density 0.521%

    No Known Activations