© 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. 8898
    Prev
    Next
    INDEX
    Explanations

    phrases involving age progression or time reference

    oai_token-act-pair · gpt-3.5-turbo

    the presence of first-person references and the past tense of "to be."

    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
     unfocusedRange
    -0.70
     applause
    -0.64
     overriding
    -0.63
    arrell
    -0.63
     emphasis
    -0.59
     implication
    -0.58
     distinguishing
    -0.58
    ply
    -0.58
     proving
    -0.57
    sites
    -0.57
    POSITIVE LOGITS
     arrived
    1.12
     began
    1.07
     debuted
    1.03
     started
    1.02
     transitioned
    0.98
     embarked
    0.97
     became
    0.94
     fled
    0.93
     died
    0.92
     entered
    0.90
    Activations Density 0.229%

    No Known Activations