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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 18900
    Prev
    Next
    INDEX
    Explanations

    the name "Mal" or related terms in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Mal" and related terms, likely indicating a focus on geographical or cultural contexts involving "Mal."

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

    No Comments

    Negative Logits
     Beir
    -0.74
    å§
    -0.73
    é¾įå¥ij士
    -0.69
     NETWORK
    -0.68
    BOOK
    -0.68
     Citation
    -0.67
    æĸ¹
    -0.66
    arettes
    -0.66
    ALK
    -0.65
    OME
    -0.65
    POSITIVE LOGITS
    icious
    1.11
    colm
    1.03
    ignant
    1.01
    adies
    1.01
    practice
    0.96
    ibu
    0.95
    pher
    0.94
    inda
    0.94
    ady
    0.93
    mort
    0.91
    Activations Density 0.013%

    No Known Activations