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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 23146
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations, specifically Greenland and Gujarat

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic locations, specifically Greenland and Gujarat

    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
    hemat
    -0.94
    otle
    -0.93
    yll
    -0.85
    intosh
    -0.84
    Afee
    -0.79
    bery
    -0.77
    choes
    -0.77
    colo
    -0.76
    ão
    -0.74
    yles
    -0.74
    POSITIVE LOGITS
     unification
    0.84
    ification
    0.76
    ified
    0.73
     Fenrir
    0.70
    fires
    0.66
     Scorpion
    0.64
    iosity
    0.64
    iant
    0.64
     riots
    0.64
    ãĥ¼ãĥĨ
    0.63
    Activations Density 0.024%

    No Known Activations