INDEX

Explanations

the word "ice" and its different forms, indicating a focus on ice-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

DoubleQuotes

-0.84

ParallelGroup

-0.68

 Anfitrión

-0.66

StoryboardSegue

-0.65

RegressionTest

-0.64

солю

-0.64

Tania

-0.63

مراجع

-0.63

országban

-0.60

dération

-0.60

POSITIVE LOGITS

ice

4.56

Ice

4.07

Ice

3.83

ice

3.18

ICE

3.03

ICE

2.63

 hielo

2.54

冰

2.36

ijs

2.26

 iced

2.23

Activations Density 0.060%

the word "ice" and its different forms, indicating a focus on ice-related concepts

No Comments

No Known Activations