© 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. 4415
    Prev
    Next
    INDEX
    Explanations

    mentions of online activities or content

    oai_token-act-pair · gpt-3.5-turbo

    references to content or activities available on the internet

    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
    itar
    -0.70
    erest
    -0.65
    ppe
    -0.62
    chest
    -0.61
    itialized
    -0.60
    IENT
    -0.59
    ariat
    -0.58
     successor
    -0.58
    OTE
    -0.56
    imental
    -0.56
    POSITIVE LOGITS
    without
    0.74
     during
    0.71
    ntil
    0.71
     Tonight
    0.69
     cheaply
    0.69
    aneously
    0.68
     without
    0.68
     until
    0.68
    eatures
    0.67
    externalActionCode
    0.66
    Activations Density 0.096%

    No Known Activations