© 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. 10-RES-JB
    11. 10210
    Prev
    Next
    INDEX
    Explanations

    references to the word "genome" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix 'ome,' indicating a focus on biological or genetic terminology

    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
    lasses
    -0.74
    idious
    -0.68
    pring
    -0.64
    ivation
    -0.62
    ive
    -0.61
     vector
    -0.61
    istas
    -0.60
     Compensation
    -0.60
    IVERS
    -0.58
    ivism
    -0.58
    POSITIVE LOGITS
    gran
    1.25
    chan
    0.93
    olithic
    0.90
    xual
    0.84
    ppa
    0.81
    gon
    0.80
    ome
    0.79
    ña
    0.76
    lla
    0.74
    istle
    0.72
    Activations Density 0.036%

    No Known Activations