INDEX

Explanations

locations and addresses, particularly in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

+#+#

-0.77

Demografía

-0.60

protoimpl

-0.58

didSet

-0.58

cshtml

-0.58

MarshalTo

-0.57

OGND

-0.56

djangoproject

-0.56

CodeAttribute

-0.55

newtheorem

-0.54

POSITIVE LOGITS

 Opal

0.56

 houſe

0.53

 Monfieur

0.53

 iſt

0.52

 myſelf

0.51

Opal

0.50

 itſelf

0.50

 Pliny

0.49

ſelves

0.49

 cavallo

0.49

Activations Density 0.175%

locations and addresses, particularly in a structured format

No Comments

No Known Activations