INDEX

Explanations

terms related to security and securing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 GenerationType

-0.49

ganggu

-0.45

tro

-0.44

 font

-0.43

wehr

-0.43

 javax

-0.43

angkutan

-0.43

TProtocol

-0.43

 Melanie

-0.42

tog

-0.42

POSITIVE LOGITS

 seal

2.00

 seals

1.88

 Seal

1.76

 sealing

1.63

Seal

1.61

seal

1.60

 sealed

1.58

 Seals

1.50

 SEAL

1.46

SEAL

1.44

Activations Density 0.059%

terms related to security and securing

No Comments

No Known Activations