INDEX

Explanations

occurrences of the word "name" and its variations in different contexts

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

name as a key

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

 JSTOR

-0.57

Cec

-0.57

⅘

-0.54

Dij

-0.54

FTFY

-0.54

 Rochester

-0.54

soph

-0.53

 Chill

-0.52

 Pollo

-0.51

stiff

-0.51

POSITIVE LOGITS

Name

1.29

 name

1.28

name

1.20

 Name

1.20

NAME

1.16

 NAME

1.12

setName

0.99

 names

0.96

 setName

0.91

 Names

0.90

Activations Density 0.061%

occurrences of the word "name" and its variations in different contexts

name as a key

No Comments

No Known Activations