© 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. 0-RES-JB
    6. 10152
    Prev
    Next
    INDEX
    Explanations

    mentions of large quantities or amounts

    oai_token-act-pair · gpt-3.5-turbo

    the term "mass" used in various contexts, particularly related to large quantities or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dogs
    -0.76
     Tycoon
    -0.74
     Bash
    -0.71
    BuyableInstoreAndOnline
    -0.70
     Sponsor
    -0.67
    arios
    -0.67
    oha
    -0.66
    quote
    -0.66
    oan
    -0.65
    hend
    -0.63
    POSITIVE LOGITS
     mass
    3.76
    mass
    2.56
     Mass
    2.27
     masses
    2.18
    Mass
    1.74
     bulk
    1.34
     masse
    1.19
     massacres
    1.13
     widespread
    1.05
     massive
    1.04
    Activations Density 0.010%

    No Known Activations