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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 2992
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical conditions and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •contextual features
    completes compound words (herbivores, leukocyte, Japonophone, e-mail). Also individually fires on polysemantic words: " entrepreneurship", " ethnicity", " piracy", " ecology", " mascara", " colonialism", " sanitation", " slavery", " agriculture", " parenting"...

    No Comments

    Negative Logits
     Frie
    -0.70
    bledon
    -0.67
    ãĥ¼ãĥĨ
    -0.63
    è¦
    -0.62
     Pengu
    -0.60
    luster
    -0.59
    bery
    -0.58
    Rober
    -0.58
     Niet
    -0.57
    Fle
    -0.57
    POSITIVE LOGITS
     ]
    0.77
     ):
    0.71
     ].
    0.69
     ·
    0.68
     )
    0.68
     :=
    0.66
     );
    0.65
     )))
    0.65
     >
    0.64
     ],
    0.62
    Activations Density 0.522%

    No Known Activations