INDEX

Explanations

elements of conversation or dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

aarrggbb

-0.84

enumii

-0.82

StructEnd

-0.81

ientôt

-0.79

WaitGroup

-0.78

ChildScrollView

-0.77

tvguidetime

-0.74

Efq

-0.74

 Houſe

-0.72

ImageContext

-0.72

POSITIVE LOGITS

0.56

partiet

0.52

0.47

0.44

ue

0.43

 zwar

0.42

well

0.42

Well

0.41

don

0.41

Activations Density 0.125%

elements of conversation or dialogue

No Comments

No Known Activations