INDEX

Explanations

expressions of introspection and personal reflection

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

emotions and emphasis

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

 Diſ

-0.78

 Reſ

-0.77

 Anſ

-0.74

 Majefty

-0.74

Efq

-0.73

 Houſe

-0.71

ſelves

-0.69

 Chriftian

-0.68

 Conſ

-0.68

 ſche

-0.66

POSITIVE LOGITS

my

0.38

HasBeenSet

0.32

 myself

0.30

 mijn

0.29

 mój

0.28

 meus

0.26

 moje

0.25

 doInBackground

0.25

 miei

0.25

 siente

0.24

Activations Density 0.047%

expressions of introspection and personal reflection

emotions and emphasis

No Comments

No Known Activations

expressions of introspection and personal reflection

emotions and emphasis

No Comments

No Known Activations