INDEX

Explanations

keywords and parameters related to functions and variable definitions in programming

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

 infatti

-0.48

."]

-0.47

ówczas

-0.46

 lenker

-0.45

"]["

-0.44

]++;

-0.43

ècie

-0.43

'."

-0.42

]';

-0.41

 нас

-0.41

POSITIVE LOGITS

opcional

0.79

HtmlAttribute

0.76

 opcional

0.73

 optional

0.71

parsedMessage

0.70

tvguidetime

0.68

?=

0.67

EDEFAULT

0.67

OPTIONAL

0.67

verwijspagina

0.65

Activations Density 0.123%

keywords and parameters related to functions and variable definitions in programming

No Comments

No Known Activations