INDEX

Explanations

terms related to improvement and effectiveness 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 @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

due

-0.48

sonaro

-0.45

 maquiagem

-0.43

níky

-0.43

sa

-0.43

ⓧ

-0.41

 stwier

-0.41

-0.39

 zaradi

-0.39

POSITIVE LOGITS

OGND

0.84

UnusedPrivate

0.73

LookAnd

0.61

SUCCEEDED

0.59

 سكانية

0.59

 Neill

0.59

 createContext

0.59

شكرا

0.58

WithIOException

0.57

Activations Density 0.863%

terms related to improvement and effectiveness in various contexts

No Comments

No Known Activations