© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 3223
    Prev
    Next
    INDEX
    Explanations

    items or concepts related to colors, especially shades of blue and red

    oai_token-act-pair · gpt-3.5-turbo

    negative connotations associated with colors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çīĪ
    -0.72
     Ces
    -0.71
     Somers
    -0.66
     ado
    -0.66
    pload
    -0.64
    OTOS
    -0.64
     TODAY
    -0.63
     Duffy
    -0.63
     BDS
    -0.63
     Rig
    -0.62
    POSITIVE LOGITS
    colored
    1.30
    skinned
    1.30
    haired
    1.23
    eyed
    1.16
    washed
    1.15
    faced
    1.15
    backed
    1.13
    clad
    1.11
    painted
    1.11
    bodied
    1.10
    Activations Density 0.060%

    No Known Activations