© 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. 9-RES-JB
    11. 17742
    Prev
    Next
    INDEX
    Explanations

    explanations or reasons for various situations or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate causes or reasons behind various phenomena or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isters
    -0.79
    strate
    -0.77
    ubs
    -0.73
    ©¶æ
    -0.73
    ctors
    -0.72
    iaries
    -0.71
    sha
    -0.71
    abase
    -0.71
    mble
    -0.70
    umbing
    -0.70
    POSITIVE LOGITS
     discrepancy
    1.26
     uptick
    1.17
     downfall
    1.16
     demise
    1.12
     discrepancies
    1.07
     disparity
    1.04
     resurgence
    1.02
     sudden
    1.02
     success
    1.01
     delay
    1.01
    Activations Density 0.262%

    No Known Activations