© 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. 6-RES-JB
    11. 7056
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    economic indicators and policy-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Copyright
    -0.59
    sin
    -0.56
    gay
    -0.54
    tain
    -0.54
    ife
    -0.53
    circ
    -0.52
    ophone
    -0.52
    pox
    -0.51
    eur
    -0.50
    dad
    -0.50
    POSITIVE LOGITS
     progressively
    0.68
     consolidate
    0.64
    è¦ļéĨĴ
    0.61
     Learns
    0.61
     gradually
    0.60
     gradual
    0.56
     concentrated
    0.55
     à¨
    0.55
    uilt
    0.54
     Proced
    0.54
    Activations Density 1.129%

    No Known Activations