© 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. 3326
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions and decisions

    oai_token-act-pair · gpt-3.5-turbo

    structures or delimiters that signify the start or end of sections 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
     Vaugh
    -0.67
    herer
    -0.67
     Seym
    -0.64
    farious
    -0.61
    swick
    -0.60
     Niet
    -0.59
    æ©
    -0.59
    retty
    -0.58
    ãĤ©
    -0.57
     advoc
    -0.55
    POSITIVE LOGITS
    ¶
    0.68
     largeDownload
    0.52
     ACPI
    0.52
     Halo
    0.52
     Xperia
    0.51
     )]
    0.51
     Allaah
    0.51
     fossil
    0.49
    ratom
    0.49
     transparency
    0.48
    Activations Density 0.755%

    No Known Activations