INDEX

Explanations

adverbial forms in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

</thead>

-0.63

culosis

-0.53

__":

-0.51

Litt

-0.50

[];

-0.47

[]=

-0.46

ImageContext

-0.46

 verfolgt

-0.46

ADEL

-0.46

ije

-0.45

POSITIVE LOGITS

 thumb

0.76

thumb

0.75

 متعلقه

0.72

 оригіналу

0.69

 Lodge

0.69

 horizon

0.67

lies

0.67

ily

0.65

Repo

0.65

 normaux

0.62

Activations Density 0.100%

adverbial forms in text

No Comments

No Known Activations