INDEX

Explanations

the word "that" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 darkest

-0.75

 busiest

-0.74

 wildest

-0.71

 exercising

-0.68

 wisest

-0.63

 noblest

-0.61

 lightest

-0.61

 disponibilités

-0.60

Portale

-0.59

 exercised

-0.59

POSITIVE LOGITS

 which

0.93

which

0.89

Which

0.79

 Which

0.77

 WHICH

0.75

MergeFrom

0.73

hich

0.72

 wich

0.72

 које

0.71

can

0.71

Activations Density 0.448%

the word "that" in various contexts

No Comments

No Known Activations