INDEX

Explanations

occurrences of the word "open"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

enderror

-0.74

 podjela

-0.70

 duquel

-0.70

 snippetHide

-0.70

AccessorTable

-0.70

didSet

-0.67

 IndexPath

-0.66

 NSCoder

-0.65

 kasarigan

-0.63

 Hezbollah

-0.62

POSITIVE LOGITS

open

4.21

 open

4.19

Open

3.75

 Open

3.66

 OPEN

3.23

OPEN

3.15

 offenen

2.41

 offene

2.35

 abierto

2.26

オープン

2.24

Activations Density 0.089%

occurrences of the word "open"

No Comments

No Known Activations