INDEX

Explanations

references to tea and tea-related activities

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

 Hecht

-0.84

Te

-0.83

ntown

-0.81

RenderAtEndOf

-0.77

 McCabe

-0.74

Te

-0.73

te

-0.71

resser

-0.71

zte

-0.70

 acci

-0.70

POSITIVE LOGITS

tea

1.50

Tea

1.33

Tea

1.25

TEA

1.12

tea

0.91

茶

0.88

 onBackPressed

0.73

 teas

0.73

 Berthe

0.71

 Châ

0.71

Activations Density 0.027%

references to tea and tea-related activities

No Comments

No Known Activations