INDEX

Explanations

specific terminology related to scientific methodologies and precision in measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Theſe

-1.01

 houſe

-1.00

ſelf

-0.99

 Jefus

-0.96

 Majefty

-0.96

 ſta

-0.94

 ſche

-0.91

Efq

-0.90

 Reſ

-0.88

 Houſe

-0.87

POSITIVE LOGITS

 >=",

0.67

0.61

 Bowden

0.61

angliski

0.58

BagLayout

0.55

genstein

0.55

getColumnIndex

0.53

ništvo

0.52

WebMethod

0.52

<",

0.52

Activations Density 0.639%

specific terminology related to scientific methodologies and precision in measurements

No Comments

No Known Activations