© 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. 2-RES-JB
    6. 10472
    Prev
    Next
    INDEX
    Explanations

    phrases related to honors or prestigious recognition

    oai_token-act-pair · gpt-3.5-turbo

    words related to honors and awards

    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
    okin
    -0.83
    angler
    -0.74
    plan
    -0.67
     hybrids
    -0.63
     Illegal
    -0.62
     cannabin
    -0.60
     illegally
    -0.60
    kit
    -0.59
     unintended
    -0.59
     vag
    -0.59
    POSITIVE LOGITS
     honoured
    1.03
     acknowled
    1.02
     honors
    0.96
     bestowed
    0.95
     honour
    0.93
     piety
    0.90
    ributes
    0.85
    brance
    0.85
    EMENT
    0.83
    thood
    0.81
    Activations Density 0.155%

    No Known Activations