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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 8540
    Prev
    Next
    INDEX
    Explanations

    phrases related to staying or remaining in a particular place or position

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "stay in" with varying contexts and implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.76
    catentry
    -0.73
    »Ĵ
    -0.72
    wcsstore
    -0.72
    UGE
    -0.67
    erity
    -0.65
    çīĪ
    -0.65
    ĪĴ
    -0.64
    MpServer
    -0.62
    è¦ļéĨĴ
    -0.62
    POSITIVE LOGITS
     indefinitely
    0.88
     afloat
    0.78
     confines
    0.77
     limbo
    0.77
     permanently
    0.75
    lishes
    0.75
     quo
    0.73
     intact
    0.72
     haunt
    0.71
     bounds
    0.70
    Activations Density 0.103%

    No Known Activations