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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 10100
    Prev
    Next
    INDEX
    Explanations

    names of individuals, likely from sports or entertainment industries

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and places

    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
    esides
    -0.74
    76561
    -0.65
    adena
    -0.65
    "),
    -0.55
    });
    -0.54
    >)
    -0.54
    assisted
    -0.53
    hers
    -0.53
    .),
    -0.53
    ").
    -0.50
    POSITIVE LOGITS
     (
    1.58
     (_
    1.44
     (-
    1.36
     ('
    1.31
     ([
    1.30
     (âĪĴ
    1.29
     (!
    1.26
     (/
    1.26
     (~
    1.25
     ()
    1.24
    Activations Density 0.282%

    No Known Activations