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. 3-RES-JB
    6. 945
    Prev
    Next
    INDEX
    Explanations

    locations or places related to the city of Dhaka

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Dhaka and its variations in name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĹĺ
    -1.01
    */(
    -0.94
     wheelchair
    -0.72
     Crimean
    -0.71
    swick
    -0.70
    izations
    -0.70
     therapy
    -0.69
    eering
    -0.68
     referrals
    -0.67
    secut
    -0.66
    POSITIVE LOGITS
     Dh
    1.15
    onest
    1.07
    awan
    1.05
    abal
    1.03
    arm
    0.98
    ancing
    0.97
    aval
    0.96
    assi
    0.92
    uran
    0.92
    izoph
    0.90
    Activations Density 0.003%

    No Known Activations