INDEX

Explanations

phrases that quantify frequency or occurrences of events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 intptr

-0.83

Bristol

-0.64

ASL

-0.64

upol

-0.63

CZ

-0.63

 karen

-0.62

 Bristol

-0.61

few

-0.61

postIndex

-0.60

itettura

-0.59

POSITIVE LOGITS

atimes

0.79

times

0.78

 TIMES

0.75

 veces

0.75

又一次

0.75

TacToe

0.73

 occasions

0.72

 TWICE

0.71

venser

0.70

trip

0.70

Activations Density 0.101%

phrases that quantify frequency or occurrences of events

No Comments

No Known Activations