INDEX

Explanations

instances of the word "where."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

ArrowToggle

-0.76

MessageTagHelper

-0.70

 Réponses

-0.63

 Vance

-0.62

 Shub

-0.59

shub

-0.59

IsMutable

-0.59

 gifts

-0.58

avance

-0.58

eraard

-0.57

POSITIVE LOGITS

 where

2.65

where

2.32

 WHERE

2.04

 Where

2.04

Where

1.97

 donde

1.92

où

1.83

WHERE

1.81

Donde

1.68

 onde

1.65

Activations Density 0.074%

instances of the word "where."

No Comments

No Known Activations