© 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. 4-RES-JB
    11. 4411
    Prev
    Next
    INDEX
    Explanations

    references to Amazon Prime services or products

    oai_token-act-pair · gpt-3.5-turbo

    references to "Prime" in various contexts

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

    No Comments

    Negative Logits
    anwhile
    -0.86
    ciplinary
    -0.80
    rouch
    -0.71
    arettes
    -0.71
    anners
    -0.70
    INESS
    -0.69
    ocket
    -0.69
     clipboard
    -0.69
    okia
    -0.68
    prus
    -0.68
    POSITIVE LOGITS
    knit
    1.06
    val
    0.81
     Directive
    0.81
     Rib
    0.79
     Prime
    0.74
    thood
    0.73
     Minister
    0.71
    digy
    0.71
    prime
    0.69
    9999
    0.68
    Activations Density 0.011%

    No Known Activations