© 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. 8-RES-JB
    11. 17759
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions that users can perform

    oai_token-act-pair · gpt-3.5-turbo

    the word "can" and its variants in different contexts within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONSORED
    -0.68
     Mant
    -0.68
    soDeliveryDate
    -0.66
    soType
    -0.61
     Execution
    -0.61
    advertising
    -0.60
     pupil
    -0.60
    pants
    -0.59
    killing
    -0.58
    Ax
    -0.57
    POSITIVE LOGITS
    't
    1.33
     choose
    1.06
     easily
    1.01
     afford
    1.00
     decide
    0.99
    adian
    0.99
     attest
    0.99
     participate
    0.98
     learn
    0.96
    NOT
    0.95
    Activations Density 0.173%

    No Known Activations