INDEX

Explanations

words and phrases related to death or dying, particularly the word "death" itself.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

references to death and 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 @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

ništ

-0.90

adpleegd

-0.84

 ComVisible

-0.84

AutoresizingMask

-0.76

AVA

-0.76

 سكانية

-0.72

 Préférences

-0.72

AddTagHelper

-0.71

IsContent

-0.70

ècie

-0.69

POSITIVE LOGITS

 śmier

0.68

 DEATH

0.65

 penalty

0.61

 death

0.60

DEATH

0.59

 toll

0.59

Death

0.58

 Death

0.57

💀

0.57

bed

0.56

Activations Density 0.107%

words and phrases related to death or dying, particularly the word "death" itself.

references to death and related themes

No Comments

No Known Activations