INDEX

Explanations

references to injuries and their consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

tagHelperRunner

-0.40

ंदीखरीदारी

-0.38

UnknownFields

-0.38

culable

-0.37

WriteBarrier

-0.36

flexGrow

-0.36

 assets

-0.36

 censiti

-0.33

 désolés

-0.33

ьаж

-0.33

POSITIVE LOGITS

 injured

0.91

injured

0.89

 wounded

0.88

 Injured

0.88

 injuries

0.87

 herido

0.85

injury

0.84

 blessé

0.82

 injury

0.82

Injury

0.81

Activations Density 0.239%

references to injuries and their consequences

No Comments

No Known Activations