INDEX

Explanations

terms and phrases related to academic publications and citations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

Digitized

-0.52

estinal

-0.48

 Balboa

-0.47

deman

-0.46

ไตล์

-0.45

HandlerContext

-0.44

complexContent

-0.43

millimeters

-0.43

martre

-0.42

 hefyd

-0.42

POSITIVE LOGITS

CODE

0.62

PREFERRED

0.62

GOTREF

0.60

ProgressHUD

0.59

ைய

0.56

يكب

0.56

0.55

windowFixed

0.55

code

0.54

[]:

0.54

Activations Density 0.267%

terms and phrases related to academic publications and citations

No Comments

No Known Activations