INDEX

Explanations

references to updates, changes, and technological processes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ged

-0.60

().__

-0.58

những

-0.55

 censi

-0.53

 vermitteln

-0.52

ITest

-0.51

adaptiveStyles

-0.49

 EnglishChoose

-0.48

 مشين

-0.48

 coolness

-0.48

POSITIVE LOGITS

 stream

0.63

smo

0.59

Искәрмәләр

0.58

 tight

0.57

 propOrder

0.56

 bright

0.55

 thick

0.55

 smooth

0.55

 straight

0.53

titleMargin

0.53

Activations Density 0.501%

references to updates, changes, and technological processes in various contexts

No Comments

No Known Activations