INDEX

Explanations

references to scientific or technical documents, specifically identifying citations and their relevant details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 AssemblyVersion

-0.93

XMLSchema

-0.78

PerformLayout

-0.78

$_['

-0.76

principalTable

-0.76

ParallelGroup

-0.75

IsContent

-0.74

 pinulongan

-0.73

ípios

-0.73

 CreateTagHelper

-0.72

POSITIVE LOGITS

sonder

0.48

SimpleName

0.47

umumkan

0.46

jelaskan

0.45

 Pich

0.45

 soie

0.43

Ữ

0.43

 merve

0.43

 pères

0.43

ParentId

0.42

Activations Density 0.681%

references to scientific or technical documents, specifically identifying citations and their relevant details

No Comments

No Known Activations