INDEX

Explanations

expressions of strong emotions or psychological states

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

Followed by "not" or a similar negative

np_acts-logits-general · gemini-2.0-flash

not matching

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

:✨

-0.63

 thereof

-0.45

 therefor

-0.42

 thereto

-0.42

 Chrift

-0.41

Meanwhile

-0.41

周泽

-0.41

 transfieras

-0.40

demic

-0.39

 pulumi

-0.38

POSITIVE LOGITS

 HasFactory

0.48

 wronged

0.44

 offend

0.42

IBAction

0.42

 vectorielles

0.42

 Olsson

0.42

Vidite

0.42

 Valdés

0.41

Архівовано

0.41

ağ

0.41

Activations Density 0.038%

expressions of strong emotions or psychological states

Followed by "not" or a similar negative

not matching

No Comments

No Known Activations