© 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. 1-RES-JB
    11. 2028
    Prev
    Next
    INDEX
    Explanations

    phrases indicating divergence from what is usual or expected

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating routine or typical occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gets
    -0.82
     Kut
    -0.74
    âĵĺ
    -0.72
    push
    -0.72
    ged
    -0.69
    him
    -0.68
    åĤ
    -0.67
    rift
    -0.65
    Lens
    -0.64
     Purpose
    -0.64
    POSITIVE LOGITS
     notor
    0.96
     compr
    0.93
     exha
    0.86
     occas
    0.86
     exting
    0.84
     conclud
    0.84
    llular
    0.83
     normally
    0.81
     encountered
    0.80
     behaved
    0.80
    Activations Density 0.005%

    No Known Activations