© 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. 7-RES-JB
    11. 1482
    Prev
    Next
    INDEX
    Explanations

    phrases related to contrasting situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation or ellipses that indicate pauses or omissions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.91
    ãĥ¼ãĥĨ
    -0.78
    artz
    -0.76
    psons
    -0.72
    isers
    -0.71
    ãĥİ
    -0.69
    ocratic
    -0.65
    izers
    -0.64
    odes
    -0.63
     plaque
    -0.63
    POSITIVE LOGITS
    nuts
    0.89
    DOWN
    0.86
    sit
    0.84
    mmmm
    0.84
    there
    0.84
    CONT
    0.81
    rss
    0.81
    cffffcc
    0.80
    etc
    0.78
    interesting
    0.77
    Activations Density 0.015%

    No Known Activations