© 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. 1-RES-JB
    11. 3644
    Prev
    Next
    INDEX
    Explanations

    references to the unit of currency "pound"

    oai_token-act-pair · gpt-3.5-turbo

    references to the pound currency

    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
    */(
    -0.76
    mberg
    -0.69
    vironment
    -0.66
    emis
    -0.65
     partName
    -0.65
    etheus
    -0.65
     Hearing
    -0.64
     WARN
    -0.64
     Occupations
    -0.63
     Sox
    -0.63
    POSITIVE LOGITS
     sterling
    1.39
     pound
    1.37
     Pound
    1.20
    cake
    0.99
    pound
    0.92
     pounds
    0.92
    nuts
    0.79
    lbs
    0.75
    stick
    0.73
     Sterling
    0.73
    Activations Density 0.011%

    No Known Activations