INDEX

Explanations

numbers and numerical values in context

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

 pleaſure

-0.81

 ſche

-0.80

 myſelf

-0.79

 itſelf

-0.78

 ―――――

-0.69

 ExecuteAsync

-0.69

 Jefus

-0.68

ſy

-0.68

 ་་

-0.67

 ſind

-0.67

POSITIVE LOGITS

 month

0.52

 person

0.51

 week

0.49

½

0.48

 Thessal

0.47

fromCharCode

0.46

person

0.46

ReusableCell

0.46

️⃣

0.45

 legged

0.45

Activations Density 0.423%

numbers and numerical values in context

No Comments

No Known Activations