INDEX

Explanations

legal terminology related to witness testimony and evidence in court

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

出版年

-0.82

IsContent

-0.73

 magasiner

-0.71

extAlignment

-0.69

RectangleBorder

-0.68

rungsseite

-0.64

Datuak

-0.64

 createSlice

-0.64

DockStyle

-0.63

 NavController

-0.61

POSITIVE LOGITS

 testimony

1.97

 witnesses

1.83

 witness

1.82

 testify

1.82

 testified

1.76

 testifying

1.74

 Testimony

1.61

 testifies

1.56

witness

1.55

 testimonies

1.53

Activations Density 0.958%

legal terminology related to witness testimony and evidence in court

No Comments

No Known Activations