INDEX

Explanations

false representations and claims regarding political affiliation and identity

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

followed by auxiliary verbs

np_acts-logits-general · gemini-2.0-flash

pretended, supposedly, believed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

BagConstraints

-0.66

 RSSSF

-0.65

__))

-0.57

 pessoal

-0.48

WIB

-0.47

 "..\..\..\

-0.46

netje

-0.46

 atle

-0.46

masing

-0.46

pumpe

-0.45

POSITIVE LOGITS

 تانيه

0.81

enumi

0.60

 ProtoMessage

0.60

SupportActionBar

0.56

tvguidetime

0.55

bootstrapcdn

0.55

 innoc

0.54

UrlResolution

0.53

getSystemService

0.52

 Commencez

0.52

Activations Density 0.291%

false representations and claims regarding political affiliation and identity

followed by auxiliary verbs

pretended, supposedly, believed

No Comments

No Known Activations