INDEX

Explanations

phrases with repetitive or conjunctional elements, particularly focusing on "and."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NullCheck

-0.64

енча

-0.58

 RUSH

-0.55

 pinulongan

-0.55

rishnan

-0.55

sig

-0.54

 Pavia

-0.53

 form

-0.52

سطس

-0.51

揄

-0.51

POSITIVE LOGITS

 UIAlert

0.71

GHIJKLM

0.71

примеча

0.70

RenderAtEndOf

0.69

nehå

0.69

pidou

0.68

TypedDataSet

0.68

]='\

0.67

JNIEnv

0.67

/-/

0.66

Activations Density 0.494%

phrases with repetitive or conjunctional elements, particularly focusing on "and."

No Comments

No Known Activations