© 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. 18521
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations or institutions named "Hills" or "bean"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Hills" and "bean," indicating a focus on locations and food items

    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
    eers
    -0.95
    eer
    -0.81
    ĥ
    -0.80
    umbnails
    -0.80
    а
    -0.78
    Ģ
    -0.76
    ²¾
    -0.75
    ģ
    -0.75
    umbn
    -0.75
    ĭ
    -0.75
    POSITIVE LOGITS
    boro
    1.00
    borough
    0.98
    dale
    0.90
     Fargo
    0.86
    steen
    0.80
    brook
    0.77
    peria
    0.73
    fields
    0.73
    abis
    0.72
    vale
    0.72
    Activations Density 0.104%

    No Known Activations