© 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. 22489
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and commands

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to technical or administrative failures and their implications

    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
    ADRA
    -0.70
     NCT
    -0.68
    Leaks
    -0.68
    WER
    -0.68
    Newsletter
    -0.65
     fortun
    -0.64
    Sov
    -0.63
    DEV
    -0.62
    Rew
    -0.62
     whistlebl
    -0.62
    POSITIVE LOGITS
     Unknown
    0.71
    olin
    0.69
     Variant
    0.68
    inav
    0.67
     Highest
    0.63
     TBA
    0.61
     Selected
    0.61
    rix
    0.61
    ente
    0.61
     Tie
    0.60
    Activations Density 1.453%

    No Known Activations