INDEX

Explanations

references to the word "each."

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

SUT

-0.70

er

-0.67

 Humphries

-0.65

Klo

-0.64

 Cosmo

-0.63

 Bons

-0.63

े

-0.62

ื้น

-0.62

Cof

-0.62

able

-0.62

POSITIVE LOGITS

EACH

1.64

 EACH

1.49

 each

1.37

 Each

1.35

each

1.33

Each

1.32

masing

1.17

각

1.11

 ciasc

1.11

JspWriter

1.09

Activations Density 0.083%

references to the word "each."

No Comments

No Known Activations