© 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. 447
    Prev
    Next
    INDEX
    Explanations

    phrases related to revival or return

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "bring back" in various contexts

    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
    eli
    -0.71
    esm
    -0.68
    ashi
    -0.68
    uss
    -0.66
     Eater
    -0.65
     understatement
    -0.64
    cture
    -0.63
     Aires
    -0.63
    alion
    -0.63
    ×IJ
    -0.62
    POSITIVE LOGITS
     home
    0.80
    wards
    0.77
    packs
    0.74
    stories
    0.74
    doors
    0.74
    seat
    0.73
     memories
    0.73
    door
    0.72
    GROUND
    0.69
    dated
    0.68
    Activations Density 0.036%

    No Known Activations