INDEX

Explanations

references to kitchen utensils and containers used in cooking

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

 Streit

-0.53

readAs

-0.51

 angin

-0.51

 Glaube

-0.47

 CommandType

-0.47

 Fuerza

-0.46

 igaz

-0.44

tilor

-0.44

læ

-0.44

Satur

-0.43

POSITIVE LOGITS

 pots

1.15

 bucket

1.09

 buckets

1.07

pot

1.06

 bowl

1.03

 Bucket

0.96

bowl

0.93

 baskets

0.93

 Pots

0.93

bucket

0.93

Activations Density 0.443%

references to kitchen utensils and containers used in cooking

No Comments

No Known Activations