© 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. 3847
    Prev
    Next
    INDEX
    Explanations

    special characters and website links

    oai_token-act-pair · gpt-3.5-turbo

    sequences of special characters, specifically multiple instances of ">>>"

    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
    ahime
    -0.82
    words
    -0.79
    wagon
    -0.79
    tackle
    -0.77
    orial
    -0.75
    ible
    -0.75
    rive
    -0.75
    ript
    -0.75
    liest
    -0.74
    laus
    -0.73
    POSITIVE LOGITS
    >>>>>>>>
    1.73
    >>>>
    1.59
    >>>
    1.46
     >>>
    1.41
    ertodd
    0.98
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    0.91
    ¶
    0.90
    _>
    0.89
    âĸĵ
    0.88
    >>
    0.86
    Activations Density 0.009%

    No Known Activations