INDEX

Explanations

references to notable individuals and their works

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

例文帳に追加

-0.56

 stats

-0.46

{#

-0.46

athlon

-0.44

-0.42

irez

-0.42

</h1>

-0.41

 wünschen

-0.41

 numeric

-0.41

 math

-0.41

POSITIVE LOGITS

 nakalista

0.86

 Essays

0.73

Selected

0.70

脚注の使い方

0.67

 Collected

0.67

Collected

0.67

NameInMap

0.67

 Selected

0.64

Essays

0.63

Lähteet

0.63

Activations Density 0.282%

references to notable individuals and their works

No Comments

No Known Activations