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

    Neuronpedia

    Jacobian LensNEW
    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. 4672
    Prev
    Next
    INDEX
    Explanations

    the word "people" preceded by adjectives or determiners

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "people" related to various contexts and sentiments

    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
    tnc
    -0.88
    united
    -0.69
    MpServer
    -0.68
     Deadly
    -0.62
    inventoryQuantity
    -0.62
     srfAttach
    -0.60
    CLASSIFIED
    -0.60
    Dialog
    -0.59
    ļéĨĴ
    -0.59
    efully
    -0.58
    POSITIVE LOGITS
     prefer
    1.16
     confuse
    1.13
     want
    1.06
     realize
    1.06
     assume
    1.06
     perceive
    1.05
     aspire
    1.01
     mistakenly
    1.00
     underestimate
    0.99
     are
    0.99
    Activations Density 0.100%

    No Known Activations