© 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. 890
    Prev
    Next
    INDEX
    Explanations

    explicitly stated or mentioned information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "explicitly"

    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
     Tycoon
    -0.92
    Score
    -0.79
    ulton
    -0.78
    ulz
    -0.68
     Balls
    -0.67
     Mile
    -0.65
     Mehran
    -0.64
    STON
    -0.64
    AMY
    -0.63
     Garry
    -0.63
    POSITIVE LOGITS
     guiActiveUn
    0.93
     contradicted
    0.85
     deline
    0.85
     differentiated
    0.83
     exempted
    0.81
     excluded
    0.80
     disav
    0.77
     tailored
    0.76
     contradicts
    0.76
     stated
    0.75
    Activations Density 0.010%

    No Known Activations