INDEX

Explanations

references to programming terminology, particularly words related to the Apache Commons libraries and coding actions like "dig."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 الحره

-0.84

FormTagHelper

-0.80

 AssemblyCulture

-0.73

tonode

-0.71

WebVitals

-0.70

 endIndex

-0.70

 configureStore

-0.69

 Савезне

-0.68

 mxArray

-0.68

SharedCtor

-0.68

POSITIVE LOGITS

Harvard

0.76

 reversed

0.73

 Harvard

0.72

Dig

0.62

dig

0.61

 backwards

0.60

 reverse

0.58

reversed

0.57

Tra

0.56

Dig

0.55

Activations Density 0.220%

references to programming terminology, particularly words related to the Apache Commons libraries and coding actions like "dig."

No Comments

No Known Activations