INDEX

Explanations

code related to URLs and network configurations

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

-0.59

-0.56

ins

-0.51

PerformLayout

-0.51

CodedInputStream

-0.50

le

-0.49

de

-0.49

</em>

-0.48

POSITIVE LOGITS

 ſtate

1.22

 houſe

1.21

 perſon

1.18

 purpoſe

1.17

 pleaſure

1.17

 ſeveral

1.15

ſelf

1.15

 ſch

1.14

 beſt

1.12

 myſelf

1.12

Activations Density 0.890%

code related to URLs and network configurations

No Comments

No Known Activations