© 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. 6-RES-JB
    11. 17024
    Prev
    Next
    INDEX
    Explanations

    phrases related to bringing something back or restoring something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "bringing back" something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aires
    -0.72
    entric
    -0.65
    itta
    -0.64
    cture
    -0.63
    uary
    -0.63
     viz
    -0.60
     Eater
    -0.60
    quin
    -0.59
    esm
    -0.59
    ities
    -0.59
    POSITIVE LOGITS
    packs
    0.90
    audi
    0.82
     memories
    0.79
    dated
    0.74
    stories
    0.74
    GROUND
    0.72
    trace
    0.71
    doors
    0.68
    woods
    0.68
    haul
    0.67
    Activations Density 0.037%

    No Known Activations