INDEX

Explanations

phrases indicating important actions, decisions, or changes in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

ulman

-0.48

lui

-0.43

WE

-0.41

ORE

-0.41

we

-0.41

 faisons

-0.41

mó

-0.41

val

-0.39

حاب

-0.39

colari

-0.38

POSITIVE LOGITS

 your

1.18

 seus

1.12

saraba

1.11

 svého

1.08

 своих

1.04

 suas

1.04

 الحره

1.03

 svých

1.03

 своего

1.00

seu

1.00

Activations Density 0.834%

phrases indicating important actions, decisions, or changes in context

No Comments

No Known Activations