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

    Neuronpedia

    APICircuit 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. 7-RES-JB
    6. 18567
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal connections or relationships

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presence or involvement of specific people or entities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artifacts
    -0.66
    ateral
    -0.64
    odder
    -0.61
     formations
    -0.59
     individually
    -0.59
    utherland
    -0.59
     instances
    -0.57
     contingency
    -0.57
    culated
    -0.57
     interconnected
    -0.57
    POSITIVE LOGITS
     whom
    1.05
    Software
    0.74
    chief
    0.73
    iac
    0.71
    Sov
    0.68
     Irma
    0.67
    @@@@@@@@
    0.64
    cci
    0.63
    chance
    0.61
     Mali
    0.61
    Activations Density 0.313%

    No Known Activations