INDEX

Explanations

specific markers or indicators of context in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

AddTagHelper

-0.57

Etimología

-0.53

󠁢

-0.47

fois

-0.47

 cons

-0.46

 mostrarán

-0.45

 JFrame

-0.44

ListTile

-0.44

SequentialGroup

-0.43

त्ति

-0.43

POSITIVE LOGITS

 such

0.76

adaptiveStyles

0.74

itinéraire

0.66

 solche

0.66

Such

0.64

 semacam

0.64

such

0.63

 چنین

0.62

 this

0.62

 sowas

0.61

Activations Density 0.225%

specific markers or indicators of context in a text

No Comments

No Known Activations