© 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. 7-RES-JB
    11. 12643
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the impact or influence of certain actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "by" indicating causation or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raq
    -0.82
    ASE
    -0.77
    ourage
    -0.76
    iatrics
    -0.75
    NAS
    -0.74
    yssey
    -0.73
    heastern
    -0.72
    eva
    -0.72
    trap
    -0.70
    ppa
    -0.69
    POSITIVE LOGITS
     virtue
    0.95
    products
    0.93
     sheer
    0.80
     nature
    0.79
     mobs
    0.76
     lightning
    0.72
     Hurricane
    0.70
     illness
    0.69
     accident
    0.69
     rumours
    0.68
    Activations Density 0.097%

    No Known Activations