© 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. 2-RES-JB
    11. 12525
    Prev
    Next
    INDEX
    Explanations

    Twitter retweets and mentions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the ">>>" symbol, indicating transitions or prompts 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
    wagon
    -0.99
    ahime
    -0.90
    laus
    -0.80
    ible
    -0.77
    enzie
    -0.77
    rive
    -0.76
    drive
    -0.74
    fare
    -0.73
    ouver
    -0.73
    alez
    -0.73
    POSITIVE LOGITS
    >>>>>>>>
    1.60
    >>>>
    1.37
    >>>
    1.15
     >>>
    0.99
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    0.84
    ertodd
    0.79
    _>
    0.75
    ¶
    0.74
    âĸĵ
    0.74
    >>
    0.74
    Activations Density 0.010%

    No Known Activations