© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23426
    Prev
    Next
    INDEX
    Explanations

    words related to irrelevance and disruptions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to levels or measurements of various concepts

    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
     Jindal
    -0.76
    ternal
    -0.68
     foremost
    -0.67
     nomine
    -0.65
     illum
    -0.61
    è¦ļéĨĴ
    -0.61
    Cmd
    -0.61
     sar
    -0.60
    dot
    -0.59
     Trou
    -0.59
    POSITIVE LOGITS
    iced
    0.85
    ibles
    0.81
    ance
    0.80
    encers
    0.75
    actory
    0.73
    ests
    0.73
    ications
    0.72
    icultural
    0.72
    encing
    0.71
    acular
    0.71
    Activations Density 0.100%

    No Known Activations