INDEX

Explanations

phrases that indicate conditions and responsibilities related to legal or official contexts

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

sentence beginnings

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

Detecting section headings or title-like phrases (short, capitalized or emphasized section labels).

oai_token-act-pair · gpt-5-mini Triggered by @vetterc0

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

ſicht

-0.97

 témoig

-0.85

 geſch

-0.85

majánló

-0.84

 ſehr

-0.83

ſehen

-0.82

iſchen

-0.82

 ſelbſt

-0.81

 wiſſen

-0.81

ſchaft

-0.81

POSITIVE LOGITS

The

0.41

0.38

If

0.37

When

0.36

if

0.36

if

0.36

Although

0.36

0.35

The

0.34

0.33

Activations Density 0.002%

phrases that indicate conditions and responsibilities related to legal or official contexts

sentence beginnings

Detecting section headings or title-like phrases (short, capitalized or emphasized section labels).

No Comments

No Known Activations