INDEX

Explanations

references to tables and figures in the text

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

heta

-0.57

 Greenway

-0.53

تح

-0.52

zub

-0.51

trage

-0.51

ộng

-0.50

 frans

-0.49

Hej

-0.49

curricular

-0.49

 оригіналу

-0.48

POSITIVE LOGITS

 Table

1.34

 table

1.28

Table

1.18

 tables

1.06

 Tables

1.01

 TABLE

0.98

 tabel

0.97

 Tabelle

0.94

TABLE

0.94

table

0.91

Activations Density 0.420%

references to tables and figures in the text

No Comments

No Known Activations