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. 18366
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to people

    oai_token-act-pair · gpt-3.5-turbo

    references to generational stereotypes, particularly about millennials

    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
     [/
    -0.94
     ['
    -0.90
     =>
    -0.89
    â̦]
    -0.88
     [+
    -0.86
    REDACTED
    -0.83
    [/
    -0.82
    _______
    -0.81
    ?,
    -0.81
    ???
    -0.79
    POSITIVE LOGITS
     itiner
    0.91
     bustling
    0.90
     pricey
    0.88
     coveted
    0.86
     tantal
    0.85
     glamorous
    0.81
     discreet
    0.80
     extravag
    0.80
     cac
    0.80
     amenities
    0.79
    Activations Density 1.025%

    No Known Activations