INDEX

Explanations

phrases that indicate the presence of items or descriptions associated with other nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 myſelf

-1.08

 houſe

-0.97

 purpoſe

-0.92

 Monfieur

-0.92

ſelf

-0.91

 iſt

-0.88

 Jefus

-0.87

 cauſe

-0.86

 ſta

-0.86

 ſche

-0.85

POSITIVE LOGITS

có

0.66

ที่มี

0.63

with

0.60

mita

0.59

no

0.57

has

0.57

af

0.56

Has

0.56

 Sinne

0.56

Activations Density 0.249%

phrases that indicate the presence of items or descriptions associated with other nouns

No Comments

No Known Activations