INDEX

Explanations

pronouns and personal references

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

words following introductory phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 rechange

-0.41

onAttach

-0.34

 lainnya

-0.33

 weiteres

-0.32

GetHashCode

-0.31

 restantes

-0.31

 Händen

-0.31

 StringTokenizer

-0.30

ChildScrollView

-0.30

 fVar

-0.30

POSITIVE LOGITS

AddTagHelper

0.68

ⓧ

0.66

 ComVisible

0.60

SharedCtor

0.60

 Photocase

0.60

httphttps

0.56

vician

0.56

UnusedPrivate

0.54

WebElementEntity

0.53

 ویکی‌پدی

0.53

Activations Density 0.013%

pronouns and personal references

words following introductory phrases

No Comments

No Known Activations