© 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. 4414
    Prev
    Next
    INDEX
    Explanations

    deep, meaningful content or interpretations in text

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "deeper" insights or meanings

    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
    ULE
    -0.76
     WATCHED
    -0.73
     Outbreak
    -0.73
    Guard
    -0.68
    ery
    -0.68
    EED
    -0.68
     overrun
    -0.68
    SR
    -0.67
    advertising
    -0.67
    gmail
    -0.66
    POSITIVE LOGITS
     than
    0.89
     insight
    0.86
     penetration
    0.83
     Than
    0.83
     layers
    0.83
     depths
    0.83
     vein
    0.82
     consideration
    0.81
     deeper
    0.81
     ditch
    0.80
    Activations Density 0.010%

    No Known Activations