© 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. 14032
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating a reason or cause

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "due" indicating reasons or causes for various situations

    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
    oola
    -0.76
    =-=-=-=-=-=-=-=-
    -0.75
     Sheep
    -0.61
    estern
    -0.60
    sat
    -0.60
    ille
    -0.60
    oho
    -0.60
    anon
    -0.59
    onen
    -0.58
    asp
    -0.57
    POSITIVE LOGITS
     diligence
    1.05
    lling
    0.76
     to
    0.75
     thereto
    0.74
    itiz
    0.69
    llers
    0.68
     solely
    0.68
     largely
    0.65
     dilig
    0.64
    giving
    0.64
    Activations Density 0.031%

    No Known Activations