INDEX

Explanations

technical terms and code-related expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

intios

-0.60

memoized

-0.58

MigrationBuilder

-0.56

UDAD

-0.55

 joint

-0.54

Linq

-0.54

submitted

-0.53

tfrac

-0.50

SourceChecksum

-0.50

pective

-0.50

POSITIVE LOGITS

AndEndTag

0.84

Efq

0.80

 avoient

0.80

 Majefty

0.75

 étoient

0.71

 fubject

0.70

 fallu

0.69

 eût

0.69

 aveug

0.69

 Jefus

0.69

Activations Density 2.578%

technical terms and code-related expressions

No Comments

No Known Activations