INDEX

Explanations

phrases and words related to location and exploration

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

ratto

-0.56

 >=",

-0.45

śl

-0.45

istics

-0.43

ynch

-0.43

toral

-0.43

CopyWith

-0.42

aliyun

-0.42

 mueble

-0.42

 solcher

-0.42

POSITIVE LOGITS

 Located

1.24

Located

1.19

 Situated

1.13

Situated

1.06

 located

0.98

 stroll

0.94

 situated

0.92

 Visitors

0.91

 visitors

0.90

Visitors

0.88

Activations Density 0.173%

phrases and words related to location and exploration

No Comments

No Known Activations