INDEX

Explanations

elements related to programming logic and conditions

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

-0.53

++];

-0.46

 know

-0.41

 refer

-0.41

 type

-0.41

 autorytatywna

-0.41

den

-0.41

 process

-0.40

ENS

-0.40

 types

-0.40

POSITIVE LOGITS

 iſt

0.83

 kasarigan

0.78

bitat

0.74

 ſte

0.72

 itſelf

0.72

ItemBackground

0.71

ibatis

0.71

 myſelf

0.70

onOptions

0.70

 bershka

0.69

Activations Density 0.121%

elements related to programming logic and conditions

No Comments

No Known Activations