INDEX

Explanations

terms related to estimation and measurement, particularly 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 @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

tvguidetime

-0.66

 OFDb

-0.62

ppet

-0.62

')

-0.61

://"

-0.60

AddHtmlAttribute

-0.59

'))

-0.59

mû

-0.59

__':

-0.57

 hữu

-0.57

POSITIVE LOGITS

 underestimate

0.80

 underestimated

0.69

 exaggerate

0.69

 outnumbered

0.65

 indisponible

0.63

 overworked

0.61

 overflow

0.58

 Overflow

0.58

 overrated

0.56

byshev

0.56

Activations Density 0.234%

terms related to estimation and measurement, particularly in scientific contexts

No Comments

No Known Activations