INDEX

Explanations

comparative phrases and expressions indicating ratios or multiples

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

 يتيمه

-0.65

+#+

-0.55

 Sulph

-0.55

getSelectedItem

-0.55

roek

-0.54

IVATE

-0.54

MessageTagHelper

-0.54

 vicin

-0.53

 createContext

-0.53

avía

-0.53

POSITIVE LOGITS

AndEndTag

0.59

СЯ

0.56

 виправивши

0.54

 halben

0.48

 ExecuteAsync

0.46

siębior

0.45

idance

0.45

 dAtA

0.44

tă

0.43

LookAnd

0.43

Activations Density 0.589%

comparative phrases and expressions indicating ratios or multiples

No Comments

No Known Activations