INDEX

Explanations

references to adversaries or enemies, as well as discussions surrounding them

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

"enemy" or its synonyms

np_acts-logits-general · gemini-2.0-flash

hostile entities and opponents

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

AddTagHelper

-0.59

Carriera

-0.58

Rhestr

-0.53

 Infórmanos

-0.50

 للمعارف

-0.50

parsedMessage

-0.50

MarshalTo

-0.49

AutoField

-0.49

devším

-0.49

addCriterion

-0.48

POSITIVE LOGITS

 Enemy

0.52

Enemy

0.46

 enemy

0.45

 Satan

0.45

 Feind

0.44

EdgeInsets

0.42

ennemi

0.41

 Dmitry

0.40

 hostile

0.38

EMY

0.38

Activations Density 0.457%

references to adversaries or enemies, as well as discussions surrounding them

"enemy" or its synonyms

hostile entities and opponents

No Comments

No Known Activations