© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 16777
    Prev
    Next
    INDEX
    Explanations

    delicate and intricately described items or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to food quality and preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gutenberg
    -0.78
    ACP
    -0.75
    MQ
    -0.73
     Mechanical
    -0.70
     Shinra
    -0.70
     Advertising
    -0.66
     Ended
    -0.66
    ĵĺ
    -0.64
     Bakr
    -0.64
     Electrical
    -0.63
    POSITIVE LOGITS
    acies
    1.38
    ately
    1.29
    acy
    1.08
    amental
    1.07
    iously
    1.04
    cheon
    0.97
    atural
    0.96
    uously
    0.94
    ulously
    0.90
    atories
    0.88
    Activations Density 0.021%

    No Known Activations