INDEX

Explanations

phrases discussing the nature and significance of experiences or memories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

<bos>

-0.54

 Nicolson

-0.52

 hoogte

-0.49

setcounter

-0.47

бовь

-0.44

 سكانية

-0.44

 javafx

-0.43

antlr

-0.42

centerY

-0.42

 Kombat

-0.41

POSITIVE LOGITS

 things

0.96

 Things

0.93

 thing

0.91

 THINGS

0.87

 THING

0.86

клопе

0.85

 חיצוניים

0.83

THING

0.83

Things

0.82

 stuffs

0.80

Activations Density 0.240%

phrases discussing the nature and significance of experiences or memories

No Comments

No Known Activations