INDEX

Explanations

programming-related terms and data structures, particularly those involving connections and configurations

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

')['

-0.62

')):

-0.58

لينكات

-0.58

LookAnd

-0.54

 unknownFields

-0.52

 localVar

-0.52

')))

-0.51

imentel

-0.50

")"

-0.50

 click

-0.50

POSITIVE LOGITS

uxxxx

0.86

RenderAtEndOf

0.76

はじめに

0.62

 NSCoder

0.61

ագրություններ

0.61

 Whig

0.55

tvguidetime

0.54

ⓘ

0.52

Véxase

0.51

########.

0.50

Activations Density 0.155%

programming-related terms and data structures, particularly those involving connections and configurations

No Comments

No Known Activations