© 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. 0-RES-JB
    11. 394
    Prev
    Next
    INDEX
    Explanations

    phrases related to leather

    oai_token-act-pair · gpt-3.5-turbo

    references to 'gathering' or related concepts

    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
     fixed
    -0.71
     forcing
    -0.67
     localization
    -0.65
    Js
    -0.64
     Pop
    -0.63
     prevalence
    -0.62
     billions
    -0.62
     Rebellion
    -0.62
     ban
    -0.61
     indebted
    -0.60
    POSITIVE LOGITS
    ather
    4.64
    athering
    2.41
    ATHER
    2.04
    athered
    1.86
    ath
    1.20
    ither
    1.15
    ater
    1.12
    ATH
    1.11
    athy
    1.04
    zbollah
    1.01
    Activations Density 0.014%

    No Known Activations