INDEX

Explanations

specific mentions of responses and contexts related to regulations or assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 houſe

-0.72

Efq

-0.67

 Houſe

-0.67

 pleaſure

-0.63

 Monfieur

-0.62

 ſta

-0.60

hagic

-0.59

WebElementEntity

-0.59

 Diſ

-0.58

Jîn

-0.58

POSITIVE LOGITS

참고

0.67

 SearchView

0.65

paramref

0.62

UnsafeEnabled

0.62

 bağlantılar

0.56

AllowAnonymous

0.55

FontOfSize

0.54

,"%

0.54

 كومونز

0.53

CompleteListener

0.52

Activations Density 1.506%

specific mentions of responses and contexts related to regulations or assessments

No Comments

No Known Activations