INDEX

Explanations

references to general concepts or ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 gales

-0.70

 Samos

-0.61

ostante

-0.61

ufe

-0.59

 Cæsar

-0.59

 счастья

-0.58

 Femen

-0.58

 uſe

-0.57

 suor

-0.57

 Desen

-0.56

POSITIVE LOGITS

 CreateTagHelper

0.94

 Thing

0.93

 THING

0.93

 resourceCulture

0.91

 things

0.90

 THINGS

0.89

 thing

0.89

 Things

0.89

Things

0.88

 happening

0.83

Activations Density 0.115%

references to general concepts or ideas

No Comments

No Known Activations