INDEX

Explanations

conditional and negative phrases related to potential or hypothetical scenarios

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

ActionCreators

-0.49

igshid

-0.47

piew

-0.45

Che

-0.45

BURGH

-0.43

>(&

-0.43

 betaal

-0.43

BIÉN

-0.43

事で

-0.42

-0.41

POSITIVE LOGITS

CppMethod

0.76

ंदीखरीदारी

0.75

 doubtnut

0.73

 itſelf

0.72

RegressionTest

0.72

 كومونز

0.71

 Theſe

0.71

izarse

0.70

balleur

0.67

 تكبرها

0.66

Activations Density 0.272%

conditional and negative phrases related to potential or hypothetical scenarios

No Comments

No Known Activations