INDEX

Explanations

geographical locations and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

estars

-0.60

 Breda

-0.51

 Unmarshal

-0.51

BASEPATH

-0.50

 iprot

-0.49

 متعلقه

-0.49

Cyfarwyddwr

-0.48

Jof

-0.48

 Zulu

-0.47

idopsis

-0.47

POSITIVE LOGITS

 lake

2.15

 Lake

2.08

Lake

1.92

 LAKE

1.81

 lakes

1.72

lake

1.65

LAKE

1.51

 Lakes

1.46

Lakes

1.40

湖

1.35

Activations Density 0.165%

geographical locations and their characteristics

No Comments

No Known Activations