INDEX

Explanations

technical jargon and mathematical notation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 дописавши

-0.79

 '\\;'

-0.76

تقاوى

-0.68

ⓧ

-0.65

Enlaces

-0.64

 rospy

-0.62

 EdgeInsets

-0.61

DebuggerNonUser

-0.61

 OkHttpClient

-0.60

Jereo

-0.60

POSITIVE LOGITS

󠁢

0.56

צלחה

0.56

えば

0.53

 hlavy

0.53

://$

0.53

 onAnimation

0.53

 Präsidenten

0.52

 kyse

0.52

 Stufe

0.50

vician

0.50

Activations Density 1.345%

technical jargon and mathematical notation

No Comments

No Known Activations