INDEX

Explanations

references to death and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ništ

-0.83

adpleegd

-0.78

########.

-0.73

AutoresizingMask

-0.72

 ComVisible

-0.72

ècie

-0.71

lgari

-0.70

 détaillés

-0.70

IBOutlet

-0.69

 سكانية

-0.69

POSITIVE LOGITS

bed

0.67

 Death

0.67

 DEATH

0.66

ly

0.65

Death

0.65

 śmier

0.65

 penalty

0.65

 death

0.65

DEATH

0.61

 deaths

0.59

Activations Density 0.095%

references to death and related concepts

No Comments

No Known Activations