INDEX

Explanations

phrases related to guidelines and instructions

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

Искәрмәләр

-0.73

atzen

-0.71

VIER

-0.67

kegaard

-0.61

Rüyada

-0.60

 Pró

-0.60

JNIEnv

-0.60

jsxFileName

-0.57

deauna

-0.57

 通販

-0.57

POSITIVE LOGITS

did

0.90

 didn

0.79

Did

0.79

 went

0.76

Did

0.75

didSet

0.75

did

0.73

 came

0.71

 differed

0.69

 took

0.69

Activations Density 0.867%

phrases related to guidelines and instructions

No Comments

No Known Activations