© 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. 7007
    Prev
    Next
    INDEX
    Explanations

    phrases related to travel and destinations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "to" followed by verbs indicating movement or action

    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
    interstitial
    -0.74
    holes
    -0.66
     centr
    -0.59
    respons
    -0.59
     ranges
    -0.58
    pointers
    -0.57
    optional
    -0.56
    unes
    -0.56
     invari
    -0.56
    raining
    -0.56
    POSITIVE LOGITS
     celebrate
    1.32
     discuss
    1.21
     commemorate
    1.20
     participate
    1.18
     receive
    1.16
     testify
    1.16
     meet
    1.16
     partake
    1.15
     retrieve
    1.15
     announce
    1.13
    Activations Density 0.130%

    No Known Activations