© 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. 7-RES-JB
    11. 3200
    Prev
    Next
    INDEX
    Explanations

    financial figures and amounts in different currencies

    oai_token-act-pair · gpt-3.5-turbo

    monetary amounts and financial information

    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
     Crow
    -0.78
     Beacon
    -0.69
     Lindsey
    -0.66
     expire
    -0.66
     Cipher
    -0.66
     Cox
    -0.65
     lax
    -0.64
     examiner
    -0.64
     deduction
    -0.62
     Squirrel
    -0.60
    POSITIVE LOGITS
    approximately
    0.90
    pictured
    0.80
    pdf
    0.80
    sic
    0.80
    currently
    0.79
    Mach
    0.75
    1981
    0.74
    pron
    0.74
    including
    0.74
    PDF
    0.74
    Activations Density 0.052%

    No Known Activations