INDEX

Explanations

general statements that indicate certainty or obviousness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Wirk

-0.55

 LCCN

-0.54

oser

-0.53

意外と

-0.52

habad

-0.52

bustion

-0.49

ijnt

-0.49

EventHandler

-0.49

 nakalista

-0.48

 Carlson

-0.48

POSITIVE LOGITS

følgelig

0.72

 obviamente

0.70

verständlich

0.69

 obviously

0.65

 évidemment

0.63

 ovviamente

0.62

 Numerade

0.62

 evidentemente

0.61

 snippetHide

0.59

 religieuses

0.59

Activations Density 0.382%

general statements that indicate certainty or obviousness

No Comments

No Known Activations