© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 13598
    Prev
    Next
    INDEX
    Explanations

    references to beliefs and worldviews held by individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    discussions about beliefs and worldviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     earthqu
    -0.75
     Mamm
    -0.74
     Bye
    -0.66
     Sever
    -0.66
     Tunnel
    -0.65
    nown
    -0.65
     Trophy
    -0.64
     rehab
    -0.63
     Ow
    -0.63
     Rockies
    -0.61
    POSITIVE LOGITS
     doctrines
    1.09
     orthodoxy
    1.07
     doctrine
    1.03
     creed
    0.92
     beliefs
    0.89
     tenets
    0.89
     dogma
    0.85
     adherents
    0.82
     ideology
    0.82
     theology
    0.81
    Activations Density 0.229%

    No Known Activations