© 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. 7-RES-JB
    11. 12578
    Prev
    Next
    INDEX
    Explanations

    expressions indicating a strong personal sentiment or opinion

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong emotional emphasis or commitment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUnfocused
    -0.72
     Gothic
    -0.69
    icist
    -0.67
    senal
    -0.63
    aic
    -0.62
    ORN
    -0.62
    Delivery
    -0.61
     Gad
    -0.61
    YING
    -0.61
     srfAttach
    -0.60
    POSITIVE LOGITS
     knew
    1.18
     owe
    1.15
     forgot
    1.08
     want
    1.04
     despise
    1.03
     need
    1.02
     ate
    0.98
     saw
    0.98
     got
    0.97
     intend
    0.97
    Activations Density 0.223%

    No Known Activations