INDEX

Explanations

abbreviations and codes related to scientific terms or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

the

-0.54

</i>

-0.47

»

-0.45

Véxase

-0.45

 simplement

-0.44

nul

-0.42

 known

-0.42

lern

-0.42

зира

-0.42

 stessi

-0.41

POSITIVE LOGITS

0.90

mybatisplus

0.86



0.84

 AssemblyTitle

0.83

TagMode

0.78

ISupport

0.78

migrationBuilder

0.76

manship

0.75

PhysRev

0.74

 Pelop

0.74

Activations Density 1.006%

abbreviations and codes related to scientific terms or measurements

No Comments

No Known Activations