INDEX

Explanations

terms related to verification and confirmation processes

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

occurrences of the word "verify" and its variations

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

verify something is true

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 Audiodateien

-0.70

Geld

-0.64

Scénario

-0.60

AfterClass

-0.59

Tas

-0.58

ÉE

-0.57

yonel

-0.57

бло

-0.57

enzie

-0.56

inoco

-0.56

POSITIVE LOGITS

 verifies

0.82

 verify

0.69

Yap

0.68

 referenties

0.68

 Verification

0.67

---*/

0.65

izable

0.65

 verific

0.65

GEBURTSDATUM

0.65

SourceChecksum

0.64

Activations Density 0.015%

terms related to verification and confirmation processes

occurrences of the word "verify" and its variations

verify something is true

No Comments

No Known Activations