INDEX

Explanations

terms related to analysis and evaluation of risks associated with products

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

followed by indefinite articles

np_acts-logits-general · gemini-2.0-flash

something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

four

-0.74

 four

-0.72

 seven

-0.71

three

-0.71

 nine

-0.70

 eight

-0.67

six

-0.66

 three

-0.66

 trois

-0.64

 five

-0.64

POSITIVE LOGITS

 algún

0.98

 bijvoorbeeld

0.89

某种

0.86

 evtl

0.86

某个

0.86

 magari

0.82

 algum

0.81

 oneself

0.80

某

0.79

 alguna

0.79

Activations Density 1.596%

terms related to analysis and evaluation of risks associated with products

followed by indefinite articles

something

No Comments

No Known Activations