Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22212
    Prev
    Next
    INDEX
    Explanations

    references to the word "Dou"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Douro River and its significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocene
    -0.92
     guiActiveUnfocused
    -0.86
     IST
    -0.85
    opathy
    -0.76
     Equip
    -0.73
    akeru
    -0.70
    Downloadha
    -0.69
    OHN
    -0.67
    ocamp
    -0.66
     Occupations
    -0.65
    POSITIVE LOGITS
    bled
    1.35
    bles
    1.31
    bling
    1.30
    plet
    1.08
    blers
    1.06
    bler
    1.03
    bt
    1.02
    pler
    0.94
    plets
    0.94
    ble
    0.93
    Activations Density 0.015%

    No Known Activations