© 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. 16754
    Prev
    Next
    INDEX
    Explanations

    names or titles preceded by 'MR'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the abbreviation "MR" and its variants

    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
    borough
    -0.65
    child
    -0.62
     planting
    -0.62
     halfway
    -0.61
     Island
    -0.59
     Islands
    -0.59
    database
    -0.59
    aea
    -0.59
     Tens
    -0.58
     Fey
    -0.57
    POSITIVE LOGITS
    MR
    3.74
     MR
    2.79
    mr
    1.80
    Ms
    1.23
    MRI
    1.19
    Mr
    1.11
    RS
    1.07
    Mrs
    1.00
    JM
    0.98
     Mr
    0.98
    Activations Density 0.008%

    No Known Activations