© 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. 4-RES-JB
    11. 3640
    Prev
    Next
    INDEX
    Explanations

    phrases related to unsubscribing or discontinuing something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to subscription management in digital content

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

    No Comments

    Negative Logits
     guiActiveUnfocused
    -0.99
     Corps
    -0.76
     Palace
    -0.75
     Passion
    -0.74
     Maker
    -0.70
    iard
    -0.69
    ordan
    -0.68
     Marin
    -0.67
     Dynamics
    -0.67
     Copenhagen
    -0.66
    POSITIVE LOGITS
    stant
    1.17
    scribe
    1.15
    mitted
    1.15
    tle
    1.05
     unsub
    1.04
    scribed
    1.03
    stantial
    1.00
    tab
    0.99
    ulously
    0.97
    verse
    0.97
    Activations Density 0.008%

    No Known Activations