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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 17678
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and reaching out

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in touch."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arcity
    -0.72
    avored
    -0.65
     Flavoring
    -0.65
    heat
    -0.64
     Drag
    -0.64
    SpaceEngineers
    -0.63
    cheat
    -0.62
     DRAG
    -0.60
    hemy
    -0.60
    MAL
    -0.58
    POSITIVE LOGITS
    Via
    0.82
    Tweet
    0.75
    osphere
    0.74
     via
    0.72
    inian
    0.70
    iste
    0.67
     arrang
    0.67
     whereabouts
    0.66
    geist
    0.65
     Via
    0.65
    Activations Density 0.048%

    No Known Activations