INDEX

Explanations

references to data packets in a networking context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

setVerticalGroup

-0.71

tanleria

-0.69

مصادر

-0.62

amera

-0.62

 multiprocessing

-0.61

hbase

-0.60

paigns

-0.60

ceq

-0.60

WithMany

-0.59

rrggbb

-0.58

POSITIVE LOGITS

Packet

0.81

 Packet

0.79

 packet

0.77

packet

0.76

 packets

0.76

Cam

0.74

er

0.68

Cam

0.64

InjectAttribute

0.63

 Freiw

0.61

Activations Density 0.036%

references to data packets in a networking context

No Comments

No Known Activations