INDEX

Explanations

references to various states in a computational or logical framework

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 bapt

-0.66

 Afonso

-0.64

 dequeue

-0.64

}),

-0.63

 *)__

-0.62

cookieParser

-0.62

ORROW

-0.61

 Donner

-0.61

Intrinsic

-0.61

 Dunlap

-0.60

POSITIVE LOGITS

 state

1.15

STATE

1.11

state

1.10

 states

1.06

 STATE

1.05

states

1.03

 StatefulWidget

1.03

 getState

0.99

stateProvider

0.97

 forState

0.96

Activations Density 0.076%

references to various states in a computational or logical framework

No Comments

No Known Activations