© 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. 10163
    Prev
    Next
    INDEX
    Explanations

    words related to maintaining or sustaining something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the necessity of maintaining or sustaining something

    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
    Interstitial
    -0.64
    NESS
    -0.64
    NetMessage
    -0.64
     GOODMAN
    -0.64
    odied
    -0.62
    ointed
    -0.60
    displayText
    -0.60
    acus
    -0.59
    lus
    -0.59
     Networks
    -0.59
    POSITIVE LOGITS
     tabs
    0.95
     pace
    0.92
     track
    0.88
     afloat
    0.86
    overs
    0.80
     alive
    0.74
     secrets
    0.73
     vigil
    0.72
    tracks
    0.72
    lower
    0.69
    Activations Density 0.037%

    No Known Activations