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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 9463
    Prev
    Next
    INDEX
    Explanations

    key phrases from statements such as reported speech, titles, and organizational roles

    oai_token-act-pair · gpt-3.5-turbo

    statements from company representatives and executives

    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
     maybe
    -0.89
     pretend
    -0.84
     scraps
    -0.84
     nodd
    -0.83
     smugg
    -0.82
     slightest
    -0.82
    ebin
    -0.80
     revolt
    -0.80
     obscure
    -0.78
     anyway
    -0.77
    POSITIVE LOGITS
    ###
    1.44
    About
    1.21
    Statement
    1.12
    Applications
    1.09
    Prior
    1.09
    Executive
    1.07
    Chair
    1.05
    Located
    1.04
    SOURCE
    1.03
    CEO
    1.03
    Activations Density 0.416%

    No Known Activations