© 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. 6-RES-JB
    11. 13747
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "handing out."

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to distributing or giving something to others

    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
     Primordial
    -0.76
    oreal
    -0.66
    STER
    -0.65
    ould
    -0.62
    ooming
    -0.62
    oved
    -0.62
    uting
    -0.61
     Minotaur
    -0.59
    antry
    -0.59
     guitarist
    -0.58
    POSITIVE LOGITS
     invitations
    0.77
    stretched
    0.76
    rants
    0.73
     flyers
    0.70
     leaflets
    0.68
    fitted
    0.68
     WARN
    0.68
    doors
    0.67
    smart
    0.67
    posts
    0.66
    Activations Density 0.046%

    No Known Activations