INDEX

Explanations

expressions of gratitude and acknowledgment towards contributors and volunteers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

styleType

-0.70

RuleContext

-0.62

 iirc

-0.60

WithIOException

-0.59

 preferably

-0.58

 getItemId

-0.58

 препратки

-0.57

 conceivably

-0.57

 IIRC

-0.56

 Desired

-0.56

POSITIVE LOGITS

 thank

0.81

 THANK

0.76

のおかげ

0.74

 Thank

0.72

 wonderful

0.72

THANK

0.71

Thank

0.70

 afgelopen

0.67

おかげ

0.67

 support

0.66

Activations Density 0.156%

expressions of gratitude and acknowledgment towards contributors and volunteers

No Comments

No Known Activations