INDEX

Explanations

prepositions and phrases indicating relationships or connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 houſe

-1.30

 purpoſe

-1.28

 myſelf

-1.23

 ſtate

-1.23

ſelves

-1.17

 itſelf

-1.17

ſelf

-1.16

 ſche

-1.12

 Houſe

-1.11

Efq

-1.10

POSITIVE LOGITS

the

1.16

0.94

"):

0.88

an

0.84

ViewFeatures

0.78

/#{

0.77

0.76

;">

0.76

}{*}{

0.75

Activations Density 0.689%

prepositions and phrases indicating relationships or connections

No Comments

No Known Activations