INDEX

Explanations

terms related to physical locations and settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enumi

-0.59

printStackTrace

-0.58

期刊论文

-0.51

pr

-0.49

capes

-0.49

 grand

-0.48

EUROPA

-0.47

出版年

-0.46



-0.45

日在

-0.45

POSITIVE LOGITS

 صوتيه

0.79

 للمعارف

0.75

 snippetHide

0.73

Efq

0.73

Rhestr

0.70

 فريبيس

0.69

CppCodeGen

0.66

 lenker

0.64

 متعلقه

0.64

IndentedString

0.64

Activations Density 0.255%

terms related to physical locations and settings

No Comments

No Known Activations