INDEX

Explanations

proper nouns, particularly names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Geplaatst

-0.96

setVerticalGroup

-0.84

Jeografia

-0.67

GEBURTSDATUM

-0.66

rungsseite

-0.61

verwijspagina

-0.59

 HttpNotFound

-0.57

InputBorder

-0.56

RetentionPolicy

-0.55

 "..\..\

-0.54

POSITIVE LOGITS

Jr

0.98

jr

0.77

III

0.75

 Filho

0.73

 мл

0.66

Sr

0.66

Esq

0.65

ová

0.63

OBE

0.62

Jr

0.62

Activations Density 0.664%

proper nouns, particularly names of individuals

No Comments

No Known Activations