INDEX

Explanations

references to attacks and aggressive actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

liğini

-0.46

 zelve

-0.46

 Vernunft

-0.46

 Picchu

-0.45

 acreditar

-0.45

 huesos

-0.44

HasBeenSet

-0.43

rungsseite

-0.42

뒀

-0.42

 désolés

-0.42

POSITIVE LOGITS

 attack

2.36

attack

2.14

 Attack

2.08

 attacks

1.98

Attack

1.93

 ATTACK

1.92

 attacked

1.84

 attacking

1.82

 Attacks

1.73

attacks

1.73

Activations Density 0.129%

references to attacks and aggressive actions

No Comments

No Known Activations