INDEX

Explanations

phrases that indicate worsening or increasing negative circumstances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

GEBURTSDATUM

-1.03

 nahilalakip

-0.88

findpost

-0.84

richTextPanel

-0.82

createCanvas

-0.82

 transfieras

-0.78

ⓧ

-0.77

JspWriter

-0.76

windowFixed

-0.75

AnchorStyles

-0.73

POSITIVE LOGITS

 further

0.96

further

0.84

 additional

0.79

Further

0.75

 thêm

0.73

 Further

0.73

 FURTHER

0.72

さらに

0.68

FURTHER

0.67

 noch

0.67

Activations Density 0.208%

phrases that indicate worsening or increasing negative circumstances

No Comments

No Known Activations