INDEX

Explanations

references to positional attributes or coordinates

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

expandindo

-1.12

MigrationBuilder

-0.93

 surla

-0.89

RenderAtEndOf

-0.76

 الرياضيه

-0.76

]--;

-0.76

ähig

-0.74

 tearDown

-0.73

Tikang

-0.73

estacks

-0.73

POSITIVE LOGITS

position

1.90

Position

1.77

POSITION

1.40

 Position

1.39

 position

1.24

 POSITION

1.20

getPosition

1.20

setPosition

1.05

positions

1.00

 getPosition

0.97

Activations Density 0.141%

references to positional attributes or coordinates

No Comments

No Known Activations