© 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. 0-RES-JB
    6. 5354
    Prev
    Next
    INDEX
    Explanations

    mentions of vinyl records

    oai_token-act-pair · gpt-3.5-turbo

    references to vinyl records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ichen
    -0.86
    ando
    -0.75
     AJ
    -0.69
    anski
    -0.69
    ADA
    -0.69
     BMI
    -0.67
    prov
    -0.67
    stadt
    -0.66
    ERSON
    -0.66
     Tess
    -0.64
    POSITIVE LOGITS
     Vinyl
    1.82
     vinyl
    1.71
     Sap
    1.47
    apon
    1.47
     Ko
    1.31
     Pir
    1.31
    ARP
    1.23
     plush
    1.22
     Squirrel
    1.07
    lest
    1.01
    Activations Density 0.035%

    No Known Activations