INDEX

Explanations

references to actions involving halting or stopping in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

zzleHttp

-0.61

ItemBackground

-0.60

 referenties

-0.60

Jeografia

-0.59

קישורים

-0.59

ricians

-0.58

ChildIndex

-0.58

RegistryLite

-0.57

➟

-0.57

enoord

-0.57

POSITIVE LOGITS

 stopped

1.36

 stop

1.30

 stops

1.23

 stopping

1.21

 Stopping

1.19

 Stopped

1.19

 stopp

1.18

 Stops

1.15

stop

1.13

stopped

1.13

Activations Density 0.186%

references to actions involving halting or stopping in various contexts

No Comments

No Known Activations