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. 21816
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to an organization or location named "Congo."

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Cong" and related terms in various contexts

    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
    ãĤ´ãĥ³
    -0.85
     Marketable
    -0.79
     Leilan
    -0.78
    IPS
    -0.77
     Gleaming
    -0.74
     logger
    -0.69
    pmwiki
    -0.69
    OHN
    -0.67
     SPORTS
    -0.67
    fulness
    -0.67
    POSITIVE LOGITS
    regation
    1.15
     Cong
    1.14
    cong
    1.08
    regate
    1.07
    ressive
    1.03
    rats
    1.00
    ression
    0.96
    reg
    0.95
    Cong
    0.90
    andan
    0.90
    Activations Density 0.010%

    No Known Activations