© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 19410
    Prev
    Next
    INDEX
    Explanations

    a mention of interest rates or economic conditions such as rates rising or being stuck at zero

    oai_token-act-pair · gpt-3.5-turbo

    important financial indicators and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kills
    -0.58
    bara
    -0.57
     Flavoring
    -0.56
    \\\\\\\\
    -0.56
    atform
    -0.55
     deserves
    -0.54
     believes
    -0.54
     himself
    -0.53
     thinks
    -0.53
    pires
    -0.52
    POSITIVE LOGITS
     expire
    0.86
     themselves
    0.85
     spaced
    0.80
    were
    0.76
     apiece
    0.75
     interchangeable
    0.74
     clustered
    0.73
     converge
    0.70
     respectively
    0.69
     vary
    0.66
    Activations Density 1.367%

    No Known Activations