INDEX

Explanations

data-related structures and elements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

opsida

-0.49

ADI

-0.46

toHave

-0.45

 Châte

-0.43

 reichen

-0.43

suites

-0.43

İstinadlar

-0.43

FieldOffset

-0.43

 Independencia

-0.43

resizingMask

-0.42

POSITIVE LOGITS

StructEnd

0.81

ibase

0.61

uxxxx

0.61

+#+#

0.60

!*\

0.59

MockMvc

0.58

 }}"></

0.56

 ligiloj

0.55

orteur

0.55

ništvo

0.55

Activations Density 0.937%

data-related structures and elements in code

No Comments

No Known Activations