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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 3-RES-JB
    6. 19699
    Prev
    Next
    INDEX
    Explanations

    dollar amounts

    oai_token-act-pair · gpt-3.5-turbo

    references to monetary values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ettings
    -0.91
     Radiation
    -0.80
     Aval
    -0.76
    earch
    -0.72
    IDES
    -0.71
     Crom
    -0.70
     Fritz
    -0.69
     à¨
    -0.69
    asma
    -0.68
    CRIP
    -0.68
    POSITIVE LOGITS
    dollar
    1.21
     dollar
    1.16
     dollars
    0.88
    naire
    0.80
    ollar
    0.79
     increments
    0.79
     sterling
    0.78
    ricular
    0.78
    hyde
    0.76
    aire
    0.76
    Activations Density 0.014%

    No Known Activations