INDEX

Explanations

references to programming or code-related elements, particularly focusing on the letter 'j' and 'J'

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Мексичка

-0.75

ousand

-0.74

%");

-0.73

%"),

-0.68

%")

-0.68

ecute

-0.63

}</

-0.63

eſ

-0.63

$")

-0.62

"],

-0.61

POSITIVE LOGITS

2.52

1.11

jskiej

0.75

 teatral

0.75

jss

0.74

 plais

0.71

jm

0.70

imath

0.70

jj

0.70

ј

0.70

Activations Density 0.156%

references to programming or code-related elements, particularly focusing on the letter 'j' and 'J'

No Comments

No Known Activations