INDEX

Explanations

names, specifically the name "Nick" or variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 betweenstory

-0.74

 препратки

-0.69

 EdgeInsets

-0.67

httphttps

-0.60

writerow

-0.60

 الحره

-0.60

twimg

-0.60

chism

-0.59

혔

-0.59

 Ibid

-0.58

POSITIVE LOGITS

name

0.63

Nic

0.63

 name

0.60

olas

0.56

named

0.55

nic

0.54

 niches

0.54

Nic

0.52

 Nicol

0.52

naming

0.50

Activations Density 0.106%

names, specifically the name "Nick" or variations of it

No Comments

No Known Activations