INDEX

Explanations

programming terms and concepts related to code functionality and logic structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

readystatechange

-0.62

-0.61

SqlDataReader

-0.60



-0.60

actionMode

-0.59

 صوتيه

-0.57

 Wiktionnaire

-0.56

prepareStatement

-0.56

 مواليد

-0.55

beginTransaction

-0.54

POSITIVE LOGITS

 because

0.91

because

0.82

 karena

0.77

 porque

0.75

 Because

0.74

porque

0.73

 BECAUSE

0.72

Because

0.72

 lantaran

0.71

 omdat

0.67

Activations Density 0.229%

programming terms and concepts related to code functionality and logic structures

No Comments

No Known Activations