INDEX

Explanations

references to toxins and poison-related themes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 كومونز

-0.77

antaranya

-0.77

resave

-0.68

\]

-0.61

PutMapping

-0.61

 newBuilder

-0.61

 فريبيس

-0.61

ualaikum

-0.60

 antaranya

-0.59

 cdti

-0.59

POSITIVE LOGITS

 poison

1.52

poison

1.42

 poisonous

1.34

Poison

1.31

 Poison

1.27

 toxic

1.24

 toxicity

1.22

 poisoning

1.20

 Toxic

1.19

toxic

1.15

Activations Density 0.489%

references to toxins and poison-related themes

No Comments

No Known Activations