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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9633
    Prev
    Next
    INDEX
    Explanations

    phrases related to publishing or releasing content

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "put out."

    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
    cious
    -0.75
    ajor
    -0.65
     Means
    -0.65
    ethy
    -0.65
    zzo
    -0.64
    hedral
    -0.63
    phrine
    -0.63
    isma
    -0.60
     Minotaur
    -0.60
    Gaming
    -0.58
    POSITIVE LOGITS
    posts
    0.96
    smart
    0.89
    stretched
    0.79
    door
    0.79
    doors
    0.74
    worn
    0.73
    rists
    0.72
    sole
    0.71
    source
    0.71
    inese
    0.69
    Activations Density 0.035%

    No Known Activations