INDEX

Explanations

occurrences of prepositions and phrases indicating relationships or references within a text

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

Text after citations or references

np_acts-logits-general · gemini-2.0-flash

document sections and references

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

aarrggbb

-0.72

 surla

-0.69

makeConstraints

-0.66

 الرياضيه

-0.64

majánló

-0.64

 ویکی‌پدی

-0.61

 ब्रेकडाउन

-0.60

 enfans

-0.59

MessageTagHelper

-0.59

 propOrder

-0.58

POSITIVE LOGITS

usepackage

0.38

__(/*!

0.35

期刊论文

0.35

CodeAttribute

0.32

0.31

window

0.31

 inside

0.30

hor

0.30

of

0.29

texttt

0.29

Activations Density 0.819%

occurrences of prepositions and phrases indicating relationships or references within a text

Text after citations or references

document sections and references

No Comments

No Known Activations