© 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. 2541
    Prev
    Next
    INDEX
    Explanations

    personal preferences or choices

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating subjective judgments or opinions

    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
    ridor
    -0.68
    ļéĨĴ
    -0.64
    ²
    -0.63
    és
    -0.61
    undown
    -0.60
    ser
    -0.60
    emale
    -0.59
    edient
    -0.59
    sha
    -0.58
    anmar
    -0.58
    POSITIVE LOGITS
    pires
    0.87
     whatsoever
    0.75
     faults
    0.72
    aign
    0.71
    inventoryQuantity
    0.71
     preached
    0.69
     chooses
    0.68
     decides
    0.68
     circumstances
    0.68
     may
    0.65
    Activations Density 0.165%

    No Known Activations