INDEX

Explanations

specific contextual elements and identifiers related to various subjects or themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

so

-0.61

-0.55

-0.50

 that

-0.49

 part

-0.48

<eos>

-0.48

we

-0.46

-0.44

-0.43

POSITIVE LOGITS

 kasarigan

1.22

 itſelf

1.21

verwijspagina

1.18

NameInMap

1.18

 myſelf

1.13

AddTagHelper

1.09

Geplaatst

1.07

Portail

1.07

ſelf

1.02

 whoſe

1.00

Activations Density 1.666%

specific contextual elements and identifiers related to various subjects or themes

No Comments

No Known Activations