INDEX

Explanations

occurrences of measurements or descriptors commonly used in a comparative manner

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

rungsseite

-0.54

оз

-0.54

最快更新

-0.54

횟

-0.53

asteroido

-0.51

談社

-0.51

новништво

-0.49

 passés

-0.47

 vägen

-0.47

ipedi

-0.46

POSITIVE LOGITS

__':

0.64

__':

0.58

 незавершена

0.56

UnitTesting

0.55

 Himo

0.55

menor

0.53

mybatisplus

0.51

 rouleau

0.51

addSubview

0.50

越来越多

0.50

Activations Density 0.103%

occurrences of measurements or descriptors commonly used in a comparative manner

No Comments

No Known Activations