INDEX

Explanations

references to accidents and disasters, specifically involving injuries or fatalities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

diego

-0.45

érrez

-0.42

новништво

-0.40

항

-0.40

isielt

-0.40

 teraz

-0.40

зна

-0.40

stånd

-0.39

 ilimit

-0.39

 understanding

-0.38

POSITIVE LOGITS

 accidents

0.92

 acidente

0.91

 accident

0.90

MemoryWarning

0.89

RectangleBorder

0.86

 injuries

0.86

 incident

0.84

accident

0.83

 incidents

0.82

 Injuries

0.82

Activations Density 0.395%

references to accidents and disasters, specifically involving injuries or fatalities

No Comments

No Known Activations