© 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. 7-RES-JB
    11. 22835
    Prev
    Next
    INDEX
    Explanations

    phrases related to causality or explanation

    oai_token-act-pair · gpt-3.5-turbo

    causal phrases or expressions indicating reasons for something occurring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.80
    arest
    -0.79
    asp
    -0.73
    arro
    -0.71
     Sheep
    -0.71
    chip
    -0.69
    adel
    -0.68
     Leone
    -0.68
    hov
    -0.68
    ivas
    -0.65
    POSITIVE LOGITS
     diligence
    1.16
    giving
    0.93
    itiz
    0.75
     cancell
    0.75
     dilig
    0.71
    gers
    0.70
    */(
    0.69
    llers
    0.69
    wcs
    0.65
    )=(
    0.65
    Activations Density 0.021%

    No Known Activations