INDEX

Explanations

identifiers in code-related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

DJANGO

-0.54

 تانيه

-0.53

 tangan

-0.48

 "..\..\..\

-0.47

 ModelExpression

-0.46

 اطلع

-0.45

uguetes

-0.44

GMENT

-0.44

 arşivlendi

-0.44

 soigne

-0.43

POSITIVE LOGITS

Personendaten

0.79

DebuggerNonUser

0.67

 disponibilités

0.67

IsContent

0.66

reactstrap

0.66

AutoScale

0.65

complexContent

0.62

Tembelea

0.62

참고

0.61

 pprint

0.61

Activations Density 0.250%

identifiers in code-related contexts

No Comments

No Known Activations