INDEX

Explanations

specific programming-related functions or keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

SharedDtor

-1.10

 tartalomajánló

-1.06

 pinulongan

-0.95

 Wikimedijinoj

-0.94

انيف

-0.91

Rohy

-0.91

DeleteBehavior

-0.83

 nakalista

-0.83

 gyhoeddwyd

-0.77

ScopeManager

-0.76

POSITIVE LOGITS

0.54

 uLocal

0.52

Eloquent

0.45

ところで

0.45

yet

0.43

 called

0.42

 thường

0.39

UserScript

0.39

IBOutlet

0.39

<bos>

0.37

Activations Density 0.020%

specific programming-related functions or keywords

No Comments

No Known Activations