INDEX

Explanations

expressions of gratitude or thanks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CSA

-0.58

NSA

-0.57

SSB

-0.57

ISA

-0.57

DSA

-0.56

CSP

-0.56

WN

-0.56

ZS

-0.55

SBR

-0.54

ESM

-0.54

POSITIVE LOGITS

 thank

0.81

 Thank

0.81

Thank

0.79

thank

0.76

ambién

0.73

 remercie

0.68

 THANK

0.68

 avoient

0.66

THANK

0.65

 feroit

0.65

Activations Density 0.004%

expressions of gratitude or thanks

No Comments

No Known Activations