INDEX

Explanations

programming constructs and syntax used in code, particularly related to function definitions and memory management

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

äher

-0.48

acker

-0.47

entown

-0.46

?!

-0.43

irée

-0.42

ionario

-0.42

 leçon

-0.42

 approu

-0.42

chafter

-0.41

POSITIVE LOGITS

 فريبيس

0.79

NewUrlParser

0.76

InputBorder

0.75

SourceChecksum

0.72

########.

0.71

↵↵

0.67

}\]

0.67

principalColumn

0.65

UnknownFields

0.65

InjectMocks

0.65

Activations Density 0.700%

programming constructs and syntax used in code, particularly related to function definitions and memory management

No Comments

No Known Activations