INDEX

Explanations

phrases and words indicative of characters returning or emerging from various situations or places

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

succ

-0.39

 succ

-0.36

utile

-0.36

 caminha

-0.35

GoTo

-0.34

ack

-0.34

 unsub

-0.34

ut

-0.33

 enne

-0.33

POSITIVE LOGITS

ьаж

1.14

GraphicsUnit

1.10

BufferException

1.03

Personendaten

1.02

 ProtoMessage

0.93

IntoConstraints

0.93

 nahilalakip

0.90

 NSCoder

0.89

 contextLoads

0.88

enumi

0.88

Activations Density 0.239%

phrases and words indicative of characters returning or emerging from various situations or places

No Comments

No Known Activations