INDEX

Explanations

words related to legal and investigative contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 actionTypes

-0.70

 initComponents

-0.58

 rigs

-0.57

tigste

-0.57

 Administrativna

-0.53

measure

-0.52

 RouterModule

-0.52

ție

-0.51

 ✭✭

-0.51

 nowadays

-0.50

POSITIVE LOGITS

 allegedly

0.82

 supuestamente

0.69

 nakalista

0.61

 alleged

0.61

 purported

0.59

 supposedly

0.58

 diduga

0.57

 apparently

0.53

RenderAtEndOf

0.53

 للاسماء

0.52

Activations Density 1.559%

words related to legal and investigative contexts

No Comments

No Known Activations