INDEX

Explanations

phrases or terms associated with legal proceedings or judicial contexts

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

Numbers within surrounding text

np_acts-logits-general · gemini-2.0-flash

historical spellings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

AndEndTag

-0.58

 BoxFit

-0.57

pyx

-0.51

:+:

-0.49

VertexArray

-0.47

civ

-0.47

ContextHolder

-0.46

 Chwiliwch

-0.46

См

-0.46

tem

-0.45

POSITIVE LOGITS

 Monfieur

0.72

 themſelves

0.67

 referenties

0.65

 ſeveral

0.63

ſelf

0.63

 greateſt

0.61

 Jefus

0.61

 raiſ

0.61

 pleaſure

0.60

 Houſe

0.60

Activations Density 0.021%

phrases or terms associated with legal proceedings or judicial contexts

Numbers within surrounding text

historical spellings

No Comments

No Known Activations