© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 3368
    Prev
    Next
    INDEX
    Explanations

    content or topics that have gained widespread attention on the internet

    oai_token-act-pair · gpt-3.5-turbo

    references to viral content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quartered
    -0.96
    fman
    -0.96
    sterdam
    -0.79
    ezvous
    -0.76
    eanor
    -0.76
    eln
    -0.75
    zzo
    -0.74
    yer
    -0.73
    haps
    -0.71
    rouch
    -0.71
    POSITIVE LOGITS
     viral
    0.96
    iously
    0.94
     sensation
    0.78
     infection
    0.77
     infections
    0.75
    irus
    0.73
    iform
    0.72
     infectious
    0.72
     Sina
    0.72
    idious
    0.71
    Activations Density 0.005%

    No Known Activations