© 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. 2630
    Prev
    Next
    INDEX
    Explanations

    phrases expressing significance or importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate communication or expression of opinions

    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
     motions
    -0.67
     submitting
    -0.65
     withdrew
    -0.64
     withdraw
    -0.63
     Meet
    -0.61
     deletion
    -0.61
     filing
    -0.61
     discuss
    -0.60
     withdrawn
    -0.60
     mailing
    -0.59
    POSITIVE LOGITS
     tremend
    0.83
    ãĥĺãĥ©
    0.82
    emi
    0.81
    itivity
    0.79
    geon
    0.77
    ends
    0.75
    paralle
    0.72
    rises
    0.71
    riz
    0.71
     volumes
    0.70
    Activations Density 0.211%

    No Known Activations