© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 15484
    Prev
    Next
    INDEX
    Explanations

    phrases related to an ongoing streak or series of events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a sequence or series of repeated occurrences

    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
    onom
    -0.88
    hod
    -0.78
    kin
    -0.74
    rol
    -0.73
    ARP
    -0.72
    adle
    -0.72
    fy
    -0.70
    info
    -0.70
    Lake
    -0.69
     Lama
    -0.68
    POSITIVE LOGITS
     consecutive
    0.97
     consecut
    0.92
     strugg
    0.90
     digits
    0.82
     bouts
    0.81
     victories
    0.81
     successive
    0.79
    dayName
    0.79
     uninterrupted
    0.78
     installments
    0.76
    Activations Density 0.008%

    No Known Activations