INDEX

Explanations

programming and function-related keywords, particularly in the context of data manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 sebou

-0.46

ChildIndex

-0.44

Pro

-0.42

wrappers

-0.41

 phương

-0.41

তথ্যসূত্র

-0.41

 føl

-0.41

<bos>

-0.41

 capitalized

-0.41

⏟

-0.41

POSITIVE LOGITS

ⓧ

0.75

 AssemblyCulture

0.73

 kasarigan

0.71

 surla

0.69

 مرئيه

0.67

thâu

0.66

 VizieR

0.61

Havolalar

0.61

parsedMessage

0.60

 Audiodateien

0.58

Activations Density 0.353%

programming and function-related keywords, particularly in the context of data manipulation

No Comments

No Known Activations

programming and function-related keywords, particularly in the context of data manipulation

No Comments

No Known Activations