© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12438
    Prev
    Next
    INDEX
    Explanations

    words related to excellence, superior quality or high performance

    oai_token-act-pair · gpt-3.5-turbo

    references to elite status or high-level performance

    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
    pty
    -0.73
    externalActionCode
    -0.71
     Drawn
    -0.70
    SourceFile
    -0.68
    FACE
    -0.68
    OUT
    -0.67
    date
    -0.66
    asta
    -0.65
    thus
    -0.65
    ventory
    -0.64
    POSITIVE LOGITS
     athlete
    0.88
     elite
    0.86
     athletes
    0.83
     acad
    0.81
     mosqu
    0.79
     prep
    0.76
     academy
    0.76
     credentials
    0.74
     prepar
    0.72
     Institution
    0.72
    Activations Density 0.015%

    No Known Activations