INDEX

Explanations

key elements and metrics related to stimulus-response patterns in experiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

itology

-0.72

sizeCache

-0.60

XmlAccessorType

-0.57

#+#

-0.57

 Hecht

-0.55

 ravi

-0.53

jooq

-0.53

estacks

-0.52

NSS

-0.51

 lohnt

-0.50

POSITIVE LOGITS

 jsPsych

1.67

 ویکی‌پدی

0.75

 nahilalakip

0.67

 Савезне

0.58

 विश्वसनीयता

0.57

chedelic

0.53

fromnode

0.52

 betweenstory

0.51

qtype

0.50

 propOrder

0.49

Activations Density 0.075%

key elements and metrics related to stimulus-response patterns in experiments

No Comments

No Known Activations