© 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. 10-RES-JB
    6. 17471
    Prev
    Next
    INDEX
    Explanations

    rumors or information that is widely spread or circulated

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the circulation and spread of information or rumors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ailable
    -0.67
    rador
    -0.65
    nect
    -0.63
    iva
    -0.62
    closure
    -0.62
    olute
    -0.61
    adra
    -0.61
    aviour
    -0.60
    ãĥĵ
    -0.59
    sin
    -0.58
    POSITIVE LOGITS
     online
    0.90
     throughout
    0.82
     around
    0.82
     louder
    0.82
    waves
    0.81
     circulated
    0.79
     furiously
    0.78
     anecd
    0.76
     frantically
    0.76
     angrily
    0.76
    Activations Density 0.141%

    No Known Activations