© 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. 4-RES-JB
    11. 534
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal opinions or reflections

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to personal thoughts 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
    ALL
    -0.80
     Mamm
    -0.70
    ARDS
    -0.69
    Naz
    -0.63
    Claim
    -0.60
     horm
    -0.60
     LOT
    -0.58
    hetti
    -0.57
     Breach
    -0.57
    gm
    -0.57
    POSITIVE LOGITS
    fulness
    0.88
     thoughts
    0.88
     aloud
    0.85
    ileaks
    0.82
     Thoughts
    0.82
    cience
    0.81
    umar
    0.77
    cient
    0.75
    eteen
    0.75
    cape
    0.73
    Activations Density 0.012%

    No Known Activations