© 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. 11-RES-JB
    11. 7575
    Prev
    Next
    INDEX
    Explanations

    organizations or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to various organizations and groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _.
    -0.72
    cffffcc
    -0.70
    ãĤĵ
    -0.69
    luster
    -0.67
    rican
    -0.63
    animate
    -0.63
    column
    -0.61
     drift
    -0.61
    ãĤ¦ãĤ¹
    -0.59
    olson
    -0.59
    POSITIVE LOGITS
     intends
    0.90
     expects
    0.85
     apologized
    0.85
     contends
    0.84
     publishes
    0.84
     appealed
    0.82
     accuses
    0.81
     insists
    0.81
     maintains
    0.79
     urged
    0.79
    Activations Density 0.168%

    No Known Activations