© 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. 3-RES-JB
    11. 11381
    Prev
    Next
    INDEX
    Explanations

    invitations to join various groups or communities

    oai_token-act-pair · gpt-3.5-turbo

    phrases encouraging participation or membership in groups or communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tiss
    -0.70
     tuber
    -0.69
    bane
    -0.65
     destro
    -0.64
    otropic
    -0.64
     Beast
    -0.61
     earthqu
    -0.61
     favorable
    -0.61
     favourable
    -0.60
    relative
    -0.60
    POSITIVE LOGITS
    Join
    0.96
    join
    0.91
     Join
    0.90
    ership
    0.84
    âĸ¬âĸ¬
    0.83
    fleet
    0.76
    nect
    0.76
    ingen
    0.73
     join
    0.72
    ters
    0.72
    Activations Density 0.021%

    No Known Activations