© 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
    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. 7739
    Prev
    Next
    INDEX
    Explanations

    references to third-party entities and relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to third-party entities or services

    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
    DAY
    -1.03
    frey
    -0.81
    bats
    -0.79
    Quantity
    -0.77
    aturday
    -0.75
    zza
    -0.74
    utenberg
    -0.73
    Hour
    -0.73
    SEE
    -0.71
    DEN
    -0.71
    POSITIVE LOGITS
     vendors
    0.95
     validation
    0.90
     intermediary
    0.88
     sellers
    0.88
     vendor
    0.84
     sensing
    0.83
     servicing
    0.82
     accommodation
    0.81
     repositories
    0.80
     verification
    0.79
    Activations Density 0.063%

    No Known Activations