INDEX

Explanations

elements related to naming conventions and definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

makeConstraints

-0.72

ähig

-0.71

umbersome

-0.71

何より

-0.68

 /\.(

-0.67

YourGuide

-0.66

 المعيارى

-0.66

hyrchwyd

-0.66

GraphicsUnit

-0.66

ånga

-0.65

POSITIVE LOGITS

 himo

0.49

 effusion

0.48

Bronnen

0.47

Географиясе

0.45

name

0.45

 twister

0.44

 withhold

0.44

thrift

0.43

 nhau

0.42

 Empieza

0.41

Activations Density 0.835%

elements related to naming conventions and definitions

No Comments

No Known Activations