© 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. 15661
    Prev
    Next
    INDEX
    Explanations

    words related to the term "pot"

    oai_token-act-pair · gpt-3.5-turbo

    references to "pot" or related terms indicating potential or conditions associated with it

    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
    IGH
    -0.69
     COR
    -0.62
     Prosecut
    -0.62
     silence
    -0.62
    :{
    -0.60
     '(
    -0.60
    ously
    -0.60
    ordinary
    -0.59
     simultane
    -0.59
     obser
    -0.59
    POSITIVE LOGITS
    assium
    1.47
    tery
    1.43
    atoes
    1.40
    entially
    1.29
    pour
    1.29
    luck
    1.24
    ential
    1.21
    ting
    1.16
    atos
    1.07
    ato
    1.06
    Activations Density 0.035%

    No Known Activations