© 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 EvalsExportsAPI 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. 2-RES-JB
    11. 6033
    Prev
    Next
    INDEX
    Explanations

    phrases related to rarity or uncommonness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rare" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abal
    -0.78
    alach
    -0.76
    iants
    -0.74
    akespeare
    -0.73
    mosp
    -0.72
     Hilton
    -0.68
    itution
    -0.68
    orthy
    -0.65
     Healthcare
    -0.65
    apa
    -0.64
    POSITIVE LOGITS
     occurrences
    1.03
     occurrence
    1.02
    ãĥ¬
    0.92
     rare
    0.91
    ãĥ©ãĥ³
    0.85
    istically
    0.83
    entimes
    0.80
    pmwiki
    0.77
     cases
    0.75
    ties
    0.75
    Activations Density 0.011%

    No Known Activations