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. 6-RES-JB
    6. 21138
    Prev
    Next
    INDEX
    Explanations

    Latin characters Ċ followed by numerical values 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    sentences indicating conflict or violence, particularly in a geopolitical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     commissions
    -0.67
    enary
    -0.65
     Minion
    -0.65
    eca
    -0.65
     Vaughn
    -0.64
     purs
    -0.64
     honors
    -0.63
    boro
    -0.63
    endas
    -0.62
    utical
    -0.62
    POSITIVE LOGITS
    Meanwhile
    1.16
    ccording
    0.98
    SPONSORED
    0.98
    However
    0.98
    Such
    0.97
    Asked
    0.95
    AFP
    0.94
    Reuters
    0.92
    Scroll
    0.90
    Foreign
    0.90
    Activations Density 0.519%

    No Known Activations