© 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. 9-RES-JB
    11. 15662
    Prev
    Next
    INDEX
    Explanations

    words related to personal beliefs, actions, and interactions

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing personal insecurity and interpersonal dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leck
    -0.67
    helps
    -0.60
    bur
    -0.59
    ONSORED
    -0.59
    geist
    -0.59
    herry
    -0.59
    eele
    -0.59
    ullah
    -0.58
     sidx
    -0.58
    itual
    -0.58
    POSITIVE LOGITS
     myself
    1.23
     thee
    0.94
     THEM
    0.84
     yours
    0.83
     them
    0.81
     ourselves
    0.78
     ya
    0.77
     YOU
    0.76
     you
    0.75
     my
    0.74
    Activations Density 1.045%

    No Known Activations