INDEX

Explanations

patterns related to structured data organization or formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

principalTable

-0.89

aarrggbb

-0.72

hyrchwyd

-0.67

 חיצוניים

-0.64

SharedCtor

-0.63

ItemLayout

-0.62

 dataSnapshot

-0.60

fortawesome

-0.60

 otomatig

-0.57

libft

-0.56

POSITIVE LOGITS

 Monfieur

0.74

 myſelf

0.69

 للمعارف

0.69

 itſelf

0.66

sizlik

0.64

 Jefus

0.61

PhysRevLett

0.59

Portale

0.58

 Majefty

0.57

ſelf

0.56

Activations Density 0.161%

patterns related to structured data organization or formatting

No Comments

No Known Activations