INDEX

Explanations

actions and interactions involving doors and visitors

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

 Rejo

-0.53

 تانيه

-0.52

ærke

-0.52

 Holman

-0.51

 Flucht

-0.50

 protoimpl

-0.49

 dich

-0.48

 Aufla

-0.48

㎢

-0.48

POSITIVE LOGITS

 door

1.46

 DOOR

1.20

 doorstep

1.20

 Door

1.18

door

1.17

Door

1.17

 knocking

1.11

 puerta

1.09

 doorbell

1.08

 knocks

1.04

Activations Density 0.133%

actions and interactions involving doors and visitors

No Comments

No Known Activations