INDEX

Explanations

dialogue or conversational exchanges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Paglinawan

-0.87

 Numerade

-0.84

 myſelf

-0.76

 itſelf

-0.76

:✨

-0.76

 ſind

-0.76

乓

-0.73

ftagPool

-0.72

 AssemblyCulture

-0.72

Efq

-0.70

POSITIVE LOGITS

UnitTesting

0.50

permitAll

0.46

Cubit

0.45

ScopeManager

0.45

RetentionPolicy

0.43

 viewType

0.43

ce

0.42

TintMode

0.41

ces

0.41

ForValue

0.40

Activations Density 0.167%

dialogue or conversational exchanges

No Comments

No Known Activations