INDEX

Explanations

references to updates and statuses regarding events or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 annually

-0.72

 jährlich

-0.71

 jähr

-0.68

 annual

-0.67

 anuales

-0.66

 years

-0.64

 Annual

-0.63

 monat

-0.61

Years

-0.61

YEARS

-0.61

POSITIVE LOGITS

 tomorrow

1.97

 yesterday

1.93

 Yesterday

1.77

yesterday

1.77

 Monday

1.71

 Thursday

1.69

 Saturday

1.68

Yesterday

1.68

 Tuesday

1.67

 Friday

1.65

Activations Density 0.756%

references to updates and statuses regarding events or situations

No Comments

No Known Activations