© 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. 14383
    Prev
    Next
    INDEX
    Explanations

    instances where something is based off of something else

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of being "based off" something

    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
    perty
    -0.78
    TPPStreamerBot
    -0.75
    uckland
    -0.70
    attled
    -0.69
    vous
    -0.68
     effected
    -0.67
    paio
    -0.67
    ittens
    -0.67
    apo
    -0.66
    eat
    -0.66
    POSITIVE LOGITS
     RPM
    0.76
     Cosponsors
    0.74
     assumption
    0.71
     Distribut
    0.67
     proprietary
    0.66
     principles
    0.65
     precedent
    0.64
     POV
    0.64
     acronym
    0.62
     Zip
    0.62
    Activations Density 0.116%

    No Known Activations