INDEX

Explanations

tokens that indicate the structure of programming or mathematical expressions

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

 ered

-0.65

entine

-0.61

ftant

-0.60

 Rein

-0.59

ftance

-0.58

]=='

-0.57

 severe

-0.56

inite

-0.56

vert

-0.56

 epitome

-0.56

POSITIVE LOGITS

 LoggerFactory

0.76

 BoxFit

0.76

 FetchType

0.69

+#+#

0.68

 становника

0.66

 ImGui

0.66

InSection

0.65

mybatisplus

0.63

󠁿

0.63

ToAction

0.60

Activations Density 1.211%

tokens that indicate the structure of programming or mathematical expressions

No Comments

No Known Activations