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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 6625
    Prev
    Next
    INDEX
    Explanations

    financial numbers and figures

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical values and financial figures within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coloring
    -0.82
     organized
    -0.82
     favorably
    -0.77
     honoring
    -0.77
     unfavorable
    -0.76
     favorable
    -0.75
     analyzed
    -0.75
     neighbor
    -0.74
     humor
    -0.74
     colored
    -0.72
    POSITIVE LOGITS
    bn
    1.55
    m
    1.47
    £
    1.32
    mn
    1.31
    cm
    1.27
    gm
    1.25
    mr
    1.21
    mb
    1.18
    mk
    1.17
    km
    1.16
    Activations Density 0.067%

    No Known Activations