© 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. 2-RES-JB
    11. 18282
    Prev
    Next
    INDEX
    Explanations

    phrases containing punctuation (specifically quotations and commas)

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their frequencies in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avorite
    -0.70
    ilitarian
    -0.70
     periphery
    -0.67
    ipop
    -0.67
    IELD
    -0.64
    dylib
    -0.62
     genetics
    -0.62
    assador
    -0.62
     blocker
    -0.62
    atto
    -0.60
    POSITIVE LOGITS
     Baal
    0.76
    sem
    0.71
    ogly
    0.70
    piring
    0.69
    ching
    0.68
     Probe
    0.68
     unfocusedRange
    0.67
     Sas
    0.65
     Bib
    0.63
     Azerbai
    0.63
    Activations Density 0.001%

    No Known Activations