Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 10615
    Prev
    Next
    INDEX
    Explanations

    financial figures, such as amounts of money

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to large quantities and monetary amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alid
    -0.65
    odox
    -0.64
    discrimination
    -0.63
    anooga
    -0.62
    etermined
    -0.61
    ivalry
    -0.61
    foundation
    -0.60
    icter
    -0.59
     contag
    -0.59
     Balk
    -0.59
    POSITIVE LOGITS
     pounds
    1.19
     yen
    1.18
     lbs
    1.10
     gallons
    1.08
     dollars
    1.07
     volts
    1.05
     miles
    1.00
     watts
    0.97
     sq
    0.96
     litres
    0.95
    Activations Density 0.146%

    No Known Activations