INDEX

Explanations

code-related keywords and elements, specifically relating to solutions and functions in programming

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

 casal

-0.43

preventDefault

-0.43

Abt

-0.43

 getItemId

-0.42

 BoxFit

-0.40

__*/

-0.40

bı

-0.39

AddWithValue

-0.38

dataclass

-0.38

 staying

-0.38

POSITIVE LOGITS

 OFDb

0.97

leetcode

0.90

 ujednoznacz

0.89

 leetcode

0.88

etCode

0.86

 متعلقه

0.81

ArrowToggle

0.80

RTEE

0.80

 ListNode

0.77

 חיצוניים

0.75

Activations Density 0.067%

code-related keywords and elements, specifically relating to solutions and functions in programming

No Comments

No Known Activations