INDEX

Explanations

specific nouns representing types of trees, people, and terms related to health and social issues

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

numbers and citations

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

 nahilalakip

-0.80

posedge

-0.79

parsedMessage

-0.72

 للمعارف

-0.71

 BoxDecoration

-0.66

 Chwiliwch

-0.66

 FetchType

-0.63

Predecesor

-0.62

 vooz

-0.61

DockStyle

-0.60

POSITIVE LOGITS

 infatti

0.33

least

0.32

libat

0.32

Node

0.31

 acompaña

0.30

uru

0.30

 least

0.30

Less

0.29

here

0.29

 less

0.29

Activations Density 0.086%

specific nouns representing types of trees, people, and terms related to health and social issues

numbers and citations

No Comments

No Known Activations