© 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. 0-RES-JB
    11. 19033
    Prev
    Next
    INDEX
    Explanations

    the word "free"

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "ree" or its variations in different contexts

    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
     CV
    -0.73
     Hitman
    -0.70
    Ô
    -0.66
     chic
    -0.65
     Cap
    -0.64
     veterans
    -0.64
     expended
    -0.64
     antic
    -0.63
     multif
    -0.63
     Veterans
    -0.62
    POSITIVE LOGITS
    ree
    4.69
    rees
    2.73
    REE
    2.42
    reek
    1.77
    reed
    1.76
    reen
    1.30
    reet
    1.26
    rey
    1.21
    reements
    1.19
    resh
    1.14
    Activations Density 0.012%

    No Known Activations