© 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. 3-RES-JB
    11. 598
    Prev
    Next
    INDEX
    Explanations

    phrases related to prayers and religious expressions

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with beliefs and pleas for support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mines
    -0.83
    xual
    -0.82
    olan
    -0.76
    izont
    -0.73
    mental
    -0.71
    neys
    -0.70
    ney
    -0.70
    lasses
    -0.69
    ohyd
    -0.68
    agle
    -0.68
    POSITIVE LOGITS
     supp
    0.78
    acebook
    0.78
    -+-+-+-+
    0.76
    lication
    0.74
     prayers
    0.74
    enance
    0.73
     precaution
    0.72
     eb
    0.70
    cloth
    0.69
     assumption
    0.65
    Activations Density 0.037%

    No Known Activations