INDEX

Explanations

topics related to language and its usage

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 blest

-0.85

 eccell

-0.73

HttpPut

-0.73

CrossRef

-0.70

 Allegretto

-0.70

 Mitar

-0.69

tagHelperRunner

-0.67

 deſt

-0.66

 Oeste

-0.65

 mío

-0.65

POSITIVE LOGITS

 language

3.72

 Language

3.33

language

3.14

Language

3.13

 LANGUAGE

2.90

 languages

2.85

 Languages

2.43

LANGUAGE

2.43

 Sprache

2.31

语言

2.25

Activations Density 0.061%

topics related to language and its usage

No Comments

No Known Activations