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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 446
    Prev
    Next
    INDEX
    Explanations

    perceived concepts or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to perception and perceived threats

    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
    trap
    -0.72
    istration
    -0.72
    sche
    -0.68
    spr
    -0.67
    ature
    -0.67
     Britann
    -0.66
    hatt
    -0.66
    etts
    -0.64
    urses
    -0.64
    olding
    -0.64
    POSITIVE LOGITS
     perceptions
    0.91
     perceived
    0.88
     unbeliev
    0.84
    ãĥ³ãĤ¸
    0.82
     cumbers
    0.79
     conflic
    0.79
     unintention
    0.78
     perceive
    0.77
    ãĥ´
    0.75
    ãĤ¨
    0.74
    Activations Density 0.012%

    No Known Activations