INDEX

Explanations

references to geographical locations or entities with the suffix "berg."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 <=",

-0.65

 ſtre

-0.63

 preſent

-0.63

 ſtate

-0.61

 Krä

-0.61

 jaundice

-0.60

Lut

-0.59

 CreateTagHelper

-0.58

 Chom

-0.57

 Chis

-0.56

POSITIVE LOGITS

berg

2.66

BERG

2.49

burg

1.79

bergs

1.72

BURG

1.62

берг

1.43

 berg

1.28

Berg

1.22

bergh

1.15

ENBERG

1.05

Activations Density 0.306%

references to geographical locations or entities with the suffix "berg."

No Comments

No Known Activations