INDEX

Explanations

occurrences 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 @ 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

migrationBuilder

-0.61

/**

-0.61

SuppressMessage

-0.60

 EconPapers

-0.57

protoimpl

-0.56

how

-0.56

Rüyada

-0.55

 AssemblyTitle

-0.55

 Ausbau

-0.54

CppMethod

-0.53

POSITIVE LOGITS

 Where

1.15

Where

1.15

WHERE

1.07

 WHERE

0.98

 Onde

0.73

点

0.73

Où

0.73

Dónde

0.68

Где

0.66

ugais

0.64

Activations Density 0.064%

occurrences of the word "where."

No Comments

No Known Activations