INDEX

Explanations

elements related to summaries and instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 terecht

-0.52

ImageContext

-0.49

็จ

-0.49

Numerology

-0.48

PreferredItem

-0.48

̍t

-0.47

 ilimit

-0.46

mayın

-0.46

avía

-0.46

isman

-0.46

POSITIVE LOGITS

ThroughAttribute

0.57

localctx

0.55

protoimpl

0.54

$}}

0.53

OrBuilder

0.52

 Lijst

0.50

 roundup

0.49

🧵

0.49

 refresher

0.49

ediakan

0.48

Activations Density 0.156%

elements related to summaries and instructions

No Comments

No Known Activations