© 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. 10931
    Prev
    Next
    INDEX
    Explanations

    time and event descriptions such as schedules and program titles

    oai_token-act-pair · gpt-3.5-turbo

    timestamps and numerical values related to events

    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
     bott
    -0.65
     downt
    -0.65
     oppressed
    -0.64
     monopol
    -0.63
     polyg
    -0.63
     HT
    -0.62
     hostage
    -0.62
    ãĤ¼ãĤ¦ãĤ¹
    -0.58
     minority
    -0.57
     exploited
    -0.56
    POSITIVE LOGITS
    amps
    0.78
    imately
    0.78
    idy
    0.76
    asse
    0.73
    alion
    0.73
    ourney
    0.73
     Refresh
    0.73
    odcast
    0.72
    athon
    0.70
    morrow
    0.69
    Activations Density 0.108%

    No Known Activations