© 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. 22854
    Prev
    Next
    INDEX
    Explanations

    numerical ranges with strong activation levels

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or ranges associated with measurements

    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
    lance
    -0.75
    Reviewer
    -0.75
    MSN
    -0.73
     Probe
    -0.72
    na
    -0.71
    Joy
    -0.69
     Prelude
    -0.68
     Painter
    -0.67
    rival
    -0.65
    SourceFile
    -0.65
    POSITIVE LOGITS
     percent
    0.90
     times
    0.84
     thousand
    0.83
     thirds
    0.83
     million
    0.82
     dozen
    0.81
     mph
    0.79
     repet
    0.79
     hundred
    0.79
     breaths
    0.77
    Activations Density 0.092%

    No Known Activations