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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 18981
    Prev
    Next
    INDEX
    Explanations

    phrases related to military or specific terms such as "Private" followed by a rank or name

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Private."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ellen
    -0.90
    itch
    -0.86
    ORN
    -0.72
    ologies
    -0.72
    ril
    -0.71
    upon
    -0.71
    ean
    -0.66
     converge
    -0.66
    orsi
    -0.65
    ves
    -0.65
    POSITIVE LOGITS
     Private
    1.13
    Private
    1.06
     Corpor
    0.92
    sector
    0.88
     Priv
    0.86
     sector
    0.85
     Sector
    0.82
     Photographer
    0.80
    isations
    0.76
     Owners
    0.74
    Activations Density 0.002%

    No Known Activations