© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 19511
    Prev
    Next
    INDEX
    Explanations

    terms related to opinions or beliefs expressed by individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal beliefs and opinions

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

    No Comments

    Negative Logits
    trap
    -0.82
     Mamm
    -0.73
    ufact
    -0.72
    seq
    -0.65
    amaz
    -0.65
    enary
    -0.64
    ursed
    -0.64
    ALL
    -0.64
    complex
    -0.62
    ce
    -0.62
    POSITIVE LOGITS
     viewpoints
    1.00
     views
    0.99
     opinions
    0.98
     beliefs
    0.85
     guiActiveUn
    0.84
     opin
    0.81
     stances
    0.79
    yip
    0.78
    hops
    0.77
     viewpoint
    0.75
    Activations Density 0.022%

    No Known Activations