INDEX

Explanations

quantitative and statistical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ViewFeatures

-0.52

-0.47

ीय

-0.43

кен

-0.40

それと

-0.36

 Cristian

-0.35

↵↵

-0.35

ance

-0.35

mise

-0.35

POSITIVE LOGITS

GOTREF

1.04

 Normdatei

1.01

GraphicsUnit

0.96

RectangleBorder

0.92

новниш

0.92

 שוליים

0.90

 Wicidata

0.88

IonicModule

0.87

InputBorder

0.87

脚注の使い方

0.87

Activations Density 0.781%

quantitative and statistical references

No Comments

No Known Activations