INDEX

Explanations

references to different states or state-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 Pilgri

-0.80

 Piac

-0.80

}),

-0.77

helves

-0.76

 fusca

-0.73

 Crusaders

-0.73

 Jezus

-0.72

 Afonso

-0.72

 encom

-0.71

 Rouen

-0.71

POSITIVE LOGITS

 State

1.43

 state

1.42

 STATE

1.36

 States

1.35

 states

1.35

states

1.34

States

1.29

state

1.28

STATE

1.25

State

1.20

Activations Density 0.125%

references to different states or state-related concepts

No Comments

No Known Activations