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. 11-RES-JB
    6. 15598
    Prev
    Next
    INDEX
    Explanations

    names of countries

    oai_token-act-pair · gpt-3.5-turbo

    references to countries, institutions, and organized groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aos
    -0.81
    cano
    -0.79
    ãĤ¦ãĤ¹
    -0.77
    }}}
    -0.73
    sonian
    -0.68
    acly
    -0.68
    nce
    -0.66
     msec
    -0.66
    WAYS
    -0.65
    nesota
    -0.65
    POSITIVE LOGITS
     surveyed
    1.07
     vying
    1.05
     affected
    1.02
     singled
    1.02
     listed
    0.98
     studied
    0.98
     hardest
    0.97
     impacted
    0.95
     eligible
    0.94
     represented
    0.93
    Activations Density 0.276%

    No Known Activations