© 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. 17245
    Prev
    Next
    INDEX
    Explanations

    phrases related to beans

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bean" and its variations

    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
    igree
    -0.83
    cffff
    -0.80
    nces
    -0.76
    untled
    -0.75
    */(
    -0.74
    ogyn
    -0.73
    ngth
    -0.72
    hematic
    -0.70
    umbn
    -0.70
     newcom
    -0.68
    POSITIVE LOGITS
    bean
    1.05
    bags
    0.94
    beans
    0.94
    bag
    0.92
    ie
    0.91
     beans
    0.84
     Beans
    0.83
    aign
    0.81
    stock
    0.79
    worker
    0.75
    Activations Density 0.023%

    No Known Activations