INDEX

Explanations

references to communication attempts and their outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

+#+#

-0.71

ברס

-0.57

 BorderRadius

-0.57

DeleteMapping

-0.56

TagMode

-0.56

ContentAsync

-0.56

 الحره

-0.55

aways

-0.54

oplasma

-0.53

>*/

-0.53

POSITIVE LOGITS

adpleegd

0.67

TypedDataSet

0.56

rrggbb

0.53

確認

0.50

 nakalista

0.50

InjectAttribute

0.50

ništ

0.47

 œil

0.46

Carriera

0.46

 regardé

0.45

Activations Density 0.410%

references to communication attempts and their outcomes

No Comments

No Known Activations