INDEX

Explanations

quantitative measurements and time durations related to events or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

 Verhältnisse

-0.48

 Verständnis

-0.45

 Geset

-0.44

 steder

-0.42

řeba

-0.40

 banyak

-0.38

 típica

-0.38

 Regionen

-0.38

 grupper

-0.38

 πάντα

-0.38

POSITIVE LOGITS

 faſt

0.71

postsleuth

0.65

 fhort

0.64

tanleria

0.61

 ſte

0.60

RTLR

0.60

ſelf

0.60

 multicolor

0.60

 wide

0.58

 ſta

0.57

Activations Density 0.296%

quantitative measurements and time durations related to events or conditions

No Comments

No Known Activations