INDEX

Explanations

code snippets related to set operations and computational processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

httphttps

-0.70

出版年

-0.63

 PyLong

-0.56

SequentialGroup

-0.54

WriteLiteral

-0.52

CodeAttribute

-0.50

heri

-0.50

mability

-0.49

CodedInputStream

-0.49

ocity

-0.48

POSITIVE LOGITS

 unique

1.08

Unique

1.06

unique

1.05

 Unique

1.03

 HashSet

0.95

 UNIQUE

0.93

HashSet

0.92

 Venn

0.90

 uniq

0.89

 intersection

0.86

Activations Density 0.639%

code snippets related to set operations and computational processes

No Comments

No Known Activations