INDEX

Explanations

quantitative measures and values 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

pierw

-0.68

ongiorno

-0.65

duh

-0.57

 OBITUARY

-0.56

ragalactic

-0.56

issner

-0.56

 éditoriale

-0.56

'],'

-0.55

حوالہ

-0.55

citep

-0.55

POSITIVE LOGITS

 amount

0.88

 average

0.85

 calculators

0.66

 total

0.65

 number

0.64

клопе

0.63

 percentage

0.62

amount

0.61

 approximate

0.61

平均

0.60

Activations Density 1.388%

quantitative measures and values in various contexts

No Comments

No Known Activations