INDEX

Explanations

technical terms related to methods and analysis in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 ostavi

-0.54

 كومونز

-0.52

dafx

-0.51

bidi

-0.49

thâu

-0.48

libft

-0.47

CJK

-0.47

LITERAL

-0.45

 noDo

-0.44

.$,

-0.43

POSITIVE LOGITS

SPATH

0.69

writerow

0.63

PRNewswire

0.63

 gynhyrchwyd

0.62

UpdateCommand

0.62

 Theſe

0.61

phinx

0.61

 myſelf

0.61

posedge

0.59

 CGSize

0.59

Activations Density 0.873%

technical terms related to methods and analysis in scientific contexts

No Comments

No Known Activations