INDEX

Explanations

expressions of formal documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

abetes

-0.91

 autorytatywna

-0.76

########.

-0.62

RenderAtEndOf

-0.62

 StatefulWidget

-0.61

LookAnd

-0.61

 GoogleFonts

-0.61

DoubleQuotes

-0.61

CodeAttribute

-0.61

fjspx

-0.61

POSITIVE LOGITS

 generally

0.58

 there

0.54

 appré

0.53

↵↵

0.50

there

0.49

 Generally

0.48

 tampoco

0.48

 Always

0.48

generally

0.48

 note

0.48

Activations Density 0.580%

expressions of formal documentation

No Comments

No Known Activations