INDEX

Explanations

references to physical barriers or walls and their interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 ujednoznacz

-0.62

invokeLater

-0.61

 صوتيه

-0.55

RTGC

-0.55

formis

-0.52

EDEFAULT

-0.50

aibo

-0.49

 INVENTION

-0.49

Atsauces

-0.48

Архівовано

-0.48

POSITIVE LOGITS

 wall

3.18

 walls

2.89

wall

2.68

 Wall

2.63

Wall

2.56

 WALL

2.53

walls

2.42

 Walls

2.42

WALL

2.31

Walls

2.18

Activations Density 0.335%

references to physical barriers or walls and their interactions

No Comments

No Known Activations