INDEX

Explanations

occurrences of the word "this"

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

 nakalista

-0.70

tadiene

-0.59

programme

-0.57

 adipis

-0.55

RTEX

-0.55

 sánh

-0.54

illips

-0.51

ριά

-0.51

TabStop

-0.51

FunctionFlags

-0.50

POSITIVE LOGITS

 دیکھیے

0.63

ритори

0.63

selves

0.62

 nahilalakip

0.62

 houſe

0.62

 Socrates

0.61

Orc

0.60

 kasarigan

0.60

 ſtate

0.59

 ruine

0.59

Activations Density 0.020%

occurrences of the word "this"

No Comments

No Known Activations