INDEX

Explanations

geographical locations and their attributes

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

<start_of_turn>user

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

 Administrativna

-0.58

MigrationBuilder

-0.50

AccessorTable

-0.50

 تضيفلها

-0.49

 <<<<<<<<<<<<<<

-0.48

TagMode

-0.47

PerformLayout

-0.47

Rhestr

-0.47

AndEndTag

-0.46

WriteTagHelper

-0.46

POSITIVE LOGITS

 Atlántico

0.43

URLException

0.41

away

0.38

 تانيه

0.38

aš

0.37

ientemente

0.36

ändert

0.36

 away

0.35

pDialog

0.35

áculo

0.35

Activations Density 0.022%

geographical locations and their attributes

<start_of_turn>user

No Comments

No Known Activations