© 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. 2187
    Prev
    Next
    INDEX
    Explanations

    phrases related to appearance or physical characteristics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "looking"

    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
    é¾į
    -0.85
    iphany
    -0.75
    chat
    -0.74
    Ëľ
    -0.74
    picking
    -0.73
    heim
    -0.72
    agi
    -0.71
    Login
    -0.71
    ille
    -0.71
    feeding
    -0.70
    POSITIVE LOGITS
     portraits
    0.73
     angles
    0.72
     samurai
    0.70
     humanoid
    0.69
     silhouette
    0.69
     silhou
    0.68
     characters
    0.67
     cardboard
    0.67
     objects
    0.67
     creature
    0.66
    Activations Density 0.047%

    No Known Activations