© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 4266
    Prev
    Next
    INDEX
    Explanations

    pronouns or nouns referring to people

    oai_token-act-pair · gpt-3.5-turbo

    references to people and their actions or experiences

    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
     Eleven
    -0.75
     Around
    -0.67
    wikipedia
    -0.66
    amaz
    -0.65
    ogue
    -0.64
     Greatest
    -0.64
     Deg
    -0.63
     Dayton
    -0.62
    icion
    -0.62
    aign
    -0.61
    POSITIVE LOGITS
     knew
    1.00
     lacked
    1.00
     didn
    0.98
    've
    0.95
     feared
    0.93
     forgot
    0.93
     got
    0.91
     couldn
    0.89
     didnt
    0.89
     hadn
    0.89
    Activations Density 0.137%

    No Known Activations