INDEX

Explanations

terms related to comparisons and relationships between entities, particularly in a contextual or experimental framework

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

-0.87

AndEndTag

-0.79

 كومونز

-0.77

 Paglinawan

-0.77

InjectMocks

-0.75

LLocation

-0.72

 fVar

-0.72

 doubtnut

-0.71

 pylint

-0.71

 itſelf

-0.71

POSITIVE LOGITS

<eos>

0.52

…

0.51

 respective

0.51

0.49

 THAN

0.47

ಃ

0.46

isling

0.46

 gynhyrchwyd

0.45

–

0.45

 future

0.45

Activations Density 0.360%

terms related to comparisons and relationships between entities, particularly in a contextual or experimental framework

No Comments

No Known Activations