© 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. 10-RES-JB
    11. 732
    Prev
    Next
    INDEX
    Explanations

    instances of a specific character

    oai_token-act-pair · gpt-3.5-turbo

    fragmented or incomplete sentences and punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     princ
    -0.81
     potentially
    -0.76
     regener
    -0.76
     util
    -0.74
     advoc
    -0.73
     dece
    -0.73
     subst
    -0.73
     previously
    -0.72
     hex
    -0.71
     correlated
    -0.71
    POSITIVE LOGITS
    Newsletter
    1.63
    Across
    1.61
    Suddenly
    1.55
    Enlarge
    1.55
    Born
    1.54
    Inside
    1.54
    Standing
    1.51
    Twenty
    1.49
    toggle
    1.47
    Then
    1.47
    Activations Density 0.417%

    No Known Activations