INDEX

Explanations

references to military fortifications or locations associated with "Fort."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

DockStyle

-0.76

 doInBackground

-0.73

rrggbb

-0.71

 stanovnika

-0.69

 Egon

-0.64

 cherchez

-0.61

Holder

-0.57

 '\\;'

-0.56

LabelTagHelper

-0.55

ună

-0.54

POSITIVE LOGITS

contentLoaded

0.68

 spot

0.68

ValueStyle

0.68

bor

0.65

 technically

0.65

:+:

0.63

 Spot

0.63

脚注の使い方

0.62

MLLoader

0.62

 nearly

0.62

Activations Density 0.139%

references to military fortifications or locations associated with "Fort."

No Comments

No Known Activations