INDEX

Explanations

code-related constructs and definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

+#+

-0.85

MigrationBuilder

-0.85

 purpoſe

-0.83

ReusableCell

-0.78

AddHtmlAttribute

-0.78

 iſt

-0.75

;"></

-0.74

encodeWith

-0.74

 MessageBoxIcon

-0.72

 ſte

-0.72

POSITIVE LOGITS

or

0.53

Big

0.53

0.51

IFUL

0.50

 action

0.48

0.47

 الحره

0.47

old

0.46

 Pacific

0.46

Activations Density 0.655%

code-related constructs and definitions

No Comments

No Known Activations