INDEX

Explanations

sections that indicate significance or importance in legal or regulatory contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

دانشنامهٔ

-0.82

 JScrollPane

-0.78

<%=

-0.76

 Grains

-0.73

 AttributeSet

-0.72

endpush

-0.72

iostream

-0.71

gatsby

-0.71

ernes

-0.70

 Chan

-0.69

POSITIVE LOGITS

1.62

1.29

1.23

1.21

1.18

1.13

1.11

Activations Density 0.111%

sections that indicate significance or importance in legal or regulatory contexts

No Comments

No Known Activations