© 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. 2143
    Prev
    Next
    INDEX
    Explanations

    names of people or entities, particularly related to statements or actions

    oai_token-act-pair · gpt-3.5-turbo

    prominent names and terms related to individuals and their roles in the context of communications and media

    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
    iazep
    -0.82
    icals
    -0.81
    nesota
    -0.80
    ngth
    -0.80
    anguage
    -0.74
    lycer
    -0.73
    oppable
    -0.71
    atonin
    -0.70
    isable
    -0.69
    ruciating
    -0.68
    POSITIVE LOGITS
     Pai
    1.15
     Mei
    0.79
    ANY
    0.72
    awei
    0.70
    anan
    0.70
     Lumpur
    0.69
     func
    0.68
    nown
    0.67
     Mahar
    0.65
     Mori
    0.64
    Activations Density 0.032%

    No Known Activations