INDEX

Explanations

descriptions of changes in levels or states in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

most

-0.51

oy

-0.50

vys

-0.47

 most

-0.46

nextDouble

-0.46

los

-0.46

la

-0.45

ולה

-0.45

OY

-0.45

()

-0.44

POSITIVE LOGITS

SourceChecksum

1.12

Slight

0.94

 briefly

0.93

 agrí

0.89

 minor

0.89

Minor

0.88

 initComponents

0.88

 MINOR

0.87

 Minor

0.86

ViewFeatures

0.86

Activations Density 0.434%

descriptions of changes in levels or states in scientific contexts

No Comments

No Known Activations