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. 19774
    Prev
    Next
    INDEX
    Explanations

    references to the city of Mosul

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Mosul

    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
    ATURE
    -0.80
    lasses
    -0.79
    tails
    -0.77
    BOOK
    -0.76
    ances
    -0.73
    reme
    -0.71
    credit
    -0.70
    chnology
    -0.69
    ered
    -0.69
    Republic
    -0.68
    POSITIVE LOGITS
     Mosul
    1.01
    igon
    0.82
     Idlib
    0.78
     Isa
    0.78
     Aleppo
    0.78
    ascus
    0.75
     neighbourhoods
    0.75
     ravaged
    0.74
     Township
    0.73
     Bosnia
    0.73
    Activations Density 0.008%

    No Known Activations