INDEX

Explanations

references to "old" or "previous" items, concepts, or ideas

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

Autoritní

-1.09

 Италијани

-0.97

ientôt

-0.95

GEBURTSDATUM

-0.95

 springfox

-0.94

kháu

-0.93

esgue

-0.92

#+#

-0.91

 незавершена

-0.89

Personendaten

-0.88

POSITIVE LOGITS

old

1.18

old

0.96

 vecchio

0.94

 vecchi

0.94

 vieux

0.91

Old

0.90

Old

0.89

 viejos

0.84

OLD

0.83

 vieja

0.81

Activations Density 0.262%

references to "old" or "previous" items, concepts, or ideas

No Comments

No Known Activations