© 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. 2-RES-JB
    6. 8033
    Prev
    Next
    INDEX
    Explanations

    sentence endings with periods

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically the period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     millenn
    -0.77
     cradle
    -0.74
     overrun
    -0.71
    rers
    -0.70
     welcome
    -0.67
    wagen
    -0.66
     unders
    -0.66
     purse
    -0.66
     appropri
    -0.65
     entitle
    -0.65
    POSITIVE LOGITS
    NET
    1.00
     .
    0.91
    -.
    0.91
    $$
    0.89
    ISO
    0.88
    _.
    0.87
    wav
    0.84
     (.
    0.82
    9999
    0.81
     Continued
    0.81
    Activations Density 0.036%

    No Known Activations