INDEX

Explanations

conditional statements or hypotheses that introduce potential outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tagHelperRunner

-0.48

ِّف

-0.42

ReusableCell

-0.42

MarshalTo

-0.41

onAttach

-0.41

annica

-0.41

 Phenomena

-0.39

paroles

-0.39

󠁴

-0.39

Datuak

-0.38

POSITIVE LOGITS

หาก

0.69

If

0.67

If

0.66

 यदि

0.65

if

0.63

Hvis

0.60

 Eğer

0.60

Если

0.60

 अगर

0.59

 Hvis

0.58

Activations Density 0.373%

conditional statements or hypotheses that introduce potential outcomes

No Comments

No Known Activations