© 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. 0-RES-JB
    6. 16738
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing advice or guidance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to advisory services and committees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $$
    -0.72
     tears
    -0.69
    phis
    -0.68
     Tears
    -0.66
     Brus
    -0.64
    comes
    -0.63
    rencies
    -0.62
    bs
    -0.61
     steal
    -0.61
    orrow
    -0.61
    POSITIVE LOGITS
     advisory
    3.96
     Advisory
    3.07
     advis
    2.02
     Advis
    1.67
     advising
    1.67
    visory
    1.65
     advisors
    1.44
     advisers
    1.34
     advisor
    1.33
     advise
    1.30
    Activations Density 0.012%

    No Known Activations