INDEX

Explanations

relationships and dependencies expressed in research contexts or academic writing

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

 henvisninger

-0.60

下载附件

-0.59

Referanser

-0.58

GRAPHS

-0.55

__(/*!

-0.54



-0.54

Außerdem

-0.53

 AssemblyProduct

-0.52

CodeAttribute

-0.51

dientemente

-0.51

POSITIVE LOGITS

__':

0.65

StructEnd

0.61

出版年

0.61

SpringBootTest

0.61

 виправивши

0.60

'))

0.59

 مرئيه

0.56

'])

0.55

__':

0.55

__":

0.54

Activations Density 1.226%

relationships and dependencies expressed in research contexts or academic writing

No Comments

No Known Activations