INDEX

Explanations

statistics and data related to approval ratings and their fluctuations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

/**

-0.61

 propOrder

-0.60

EDEFAULT

-0.57

essero

-0.57

unków

-0.55

Personendaten

-0.54

還要

-0.53

 Será

-0.52

endiri

-0.52

+#+

-0.52

POSITIVE LOGITS

has

2.66

has

1.72

Has

1.60

Has

1.48

 telah

1.39

 heeft

1.28

HAS

1.22

 đã

1.19

 έχει

1.14

 hath

1.11

Activations Density 0.912%

statistics and data related to approval ratings and their fluctuations

No Comments

No Known Activations