INDEX

Explanations

phrases related to statistical analysis and measurement precision in scientific studies

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

"[Something] within [a range/limit]"

np_acts-logits-general · gemini-2.0-flash

within acceptable ranges or limits

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

MetaType

-0.59

recated

-0.56

CodedInputStream

-0.56

adpleegd

-0.55

 تكبرها

-0.55

 haste

-0.53

 EconPapers

-0.53

curse

-0.52

 demurrer

-0.52

 snippetHide

-0.51

POSITIVE LOGITS

+/-

1.08

 range

1.07

 deviation

1.07

 tolerances

1.07

±

1.06

 tolerance

1.05

 Abweich

1.05

 deviations

1.01

(±

0.98

+-

0.97

Activations Density 0.865%

phrases related to statistical analysis and measurement precision in scientific studies

"[Something] within [a range/limit]"

within acceptable ranges or limits

No Comments

No Known Activations