© 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. 2-RES-JB
    6. 23645
    Prev
    Next
    INDEX
    Explanations

    proper names related to Wes Anderson

    oai_token-act-pair · gpt-3.5-turbo

    references to Wes Anderson and related names

    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
     bulls
    -0.77
    istically
    -0.73
     vested
    -0.70
    istics
    -0.67
    matically
    -0.65
     waning
    -0.64
     fathers
    -0.64
     carriers
    -0.64
     susceptibility
    -0.63
     whims
    -0.63
    POSITIVE LOGITS
    nesday
    1.18
     Wes
    1.07
    apon
    0.88
    coe
    0.88
     Wel
    0.84
    retch
    0.80
    boro
    0.78
    erk
    0.78
    farm
    0.74
    minster
    0.73
    Activations Density 0.008%

    No Known Activations