© 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. 9032
    Prev
    Next
    INDEX
    Explanations

    Instagram usernames or mentions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Instagram

    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
     Tone
    -0.71
     Pose
    -0.71
    DEN
    -0.65
     Siren
    -0.62
     Waterloo
    -0.61
     Freder
    -0.60
     Seasons
    -0.60
    ALD
    -0.60
     QC
    -0.60
    livious
    -0.59
    POSITIVE LOGITS
    itution
    1.39
    itute
    1.38
    inst
    1.16
    itutional
    1.14
    ruction
    1.08
    itutes
    1.06
    agram
    1.02
    inct
    0.95
    alling
    0.94
    ument
    0.91
    Activations Density 0.006%

    No Known Activations